id int64 393k 2.82B | repo stringclasses 68
values | title stringlengths 1 936 | body stringlengths 0 256k ⌀ | labels stringlengths 2 508 | priority stringclasses 3
values | severity stringclasses 3
values |
|---|---|---|---|---|---|---|
2,555,113,843 | neovim | multigrid UI: floating windows move when multigrid UI reconnects | ### Problem
When a multigrid UI reconnects, the floating windows move and the contents becomes empty.
### Steps to reproduce
1. Start a server `nvim --headless --listen /tmp/nvim.socket`
2. Connect with a multigrid UI like Neovide `neovide --server /tmp/nvim.socket`
3. Open a floating window like telescope
4. Disconnect from the server `:call chanclose(nvim_list_uis()[0].chan)`
5. Reconnect `neovide --server /tmp/nvim.socket`
6. Observe that the layout has changed like below
Before:
After:
### Expected behavior
The layout and the contents should not change
### Nvim version (nvim -v)
0.10.1 and latest master
### Vim (not Nvim) behaves the same?
N/A
### Operating system/version
Arch Linux
### Terminal name/version
Neovide 0.13.3
### $TERM environment variable
N/A
### Installation
pacman | bug,ui,ui-extensibility | low | Minor |
2,555,115,608 | neovim | multigrid UI: window contents disappear when multigrid UI reconnects | ### Problem
When a multigrid UI reconnects, the window content disappears and only the background is visible
### Steps to reproduce
1. Start a server `nvim --headless --listen /tmp/nvim.socket`
2. Connect with a multigrid UI like Neovide `neovide --server /tmp/nvim.socket`
3. Open a buffer
4. Disconnect from the server `:call chanclose(nvim_list_uis()[0].chan)`
5. Reconnect `neovide --server /tmp/nvim.socket`
Observe that the window is empty:
Before:
After:
### Expected behavior
The window should keep it's contents.
### Nvim version (nvim -v)
0.10.1 and latest master
### Vim (not Nvim) behaves the same?
N/A
### Operating system/version
Arch Linux
### Terminal name/version
Neovide 0.13.3
### $TERM environment variable
N/A
### Installation
pacman | bug,ui,ui-extensibility | low | Minor |
2,555,129,549 | neovim | UI protocol: expose floatwin composition order (comp_index) to UIs | ### Problem
Neovim uses a hidden internal composition order, which determines the order the floating windows with the same z-index are drawn. Many UIs, including the very widespread telecope relies on this order to build the UIs. In particular, a there's no alpha blending between the windows of the same z-index, the last window in the index will always be used.
A GUI like, Neovide, need to respect this order and do the same type of rendering, or things will look wrong. So that's in fact what we are doing right now, I reverse engineered the algorithm and duplicated it in Neovide [here](https://github.com/neovide/neovide/pull/2612). But it only works when the UI is connected from the start, and we receive absolutely all the events. It's also very fragile.
### Expected behavior
The internal composition order is exposed in the UI protocol.
NOTE: Another solution would be to require the whole plugin world to stop using overlapping z-indices. But this does still not work correctly in Neovide, because then we need a way to control the shadow casting and blur. Threating the whole z-index as one layer, is much easier to understand and does not require plugin authors to add additional Neovide specific annotations. | enhancement,ui-extensibility,floatwin | low | Major |
2,555,151,120 | svelte | Consider switching to a more mature parser | ### Describe the problem
There are many issues that have `acorn-typescript` as the upstream cause (#13179, #13125, #13409, #13188, [more](https://github.com/sveltejs/svelte/issues?q=acorn)), but `acorn-typescript` is [abandoned](https://github.com/TyrealHu/acorn-typescript/issues/61). It also has several open issues that would need to be addressed once forked or collaboration access is granted.
### Describe the proposed solution
One of the following:
- Fork `acorn-typescript`. The svelte team would become the primary maintainers but it wouldn't require any changes to the svelte source code.
- Use an alternate parser, such as [`swc`](https://swc.rs/docs/usage/core#parse) or [`oxc`](https://github.com/oxc-project/oxc?tab=readme-ov-file#-ast-and-parser). SWC seems to use the same AST types as acorn, but oxc advertises faster speeds. These parsers are much more mature than `acorn-typescript` and are obviously actively maintained. (note: oxc would require changes to both esrap and the svelte source)
My vote would be for the latter. The downsides (bigger dependencies and changes to svelte's source) are outweighed by the long-term advantage of using a more reliable library.
### Importance
nice to have | compiler,needs discussion | medium | Major |
2,555,163,651 | vscode | `editor.fontLigatuers` doesn't wotk if the string is long | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes/No
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.1
- OS Version: windows 10
Steps to Reproduce:
1. Install `iosevka` font https://github.com/be5invis/Iosevka/releases/tag/v31.7.1 which has many variants
2. use the font in vscode and apply a long `fontLigatures` setting:
```
"editor.fontLigatures": "'dlig','ss20','cv06' 1,'cv08' 2,'cv09' 1,'cv10' 6,'cv17' 11,'cv19' 3,'cv20' 1,'cv26' 8,'cv27' 21,'cv28' 4,'cv36' 4,'cv37' 4,'cv39' 7,'cv42' 6,'cv44' 8,'cv45' 1,'cv47' 8,'cv48' 30,'cv49' 8,'cv50' 4,'cv51' 9,'cv52' 5,'cv54' 3,'cv55' 8,'VSAJ' 7,'VSAK' 2,'VSAL' 7,'VSAM' 7,'VLAG' 2",
```
The variant features do not work in this case, however, they will work if the string is sufficiently shortened:
```
"editor.fontLigatures": "'dlig','cv06' 1,'cv44' 8,'cv45' 1,'cv47' 8,'cv49' 8,'cv50' 4,'cv51' 9,'cv52' 5,'cv54' 3,'cv55' 8,'VSAJ' 7,'VSAK' 2,'VSAL' 7,'VSAM' 7,'VLAG' 2,'cv48' 30",
```
There seems to be a length limit on this string around 150 bytes, maybe increase it to 1024, etc.
| bug,font-rendering,confirmation-pending | low | Critical |
2,555,192,845 | svelte | Slide transition of svelte 5 does not work correctly on iOS | ### Describe the bug
A slide transition on iOS/Safari does not „slide in“ an element step by step. Instead the content is show in one step and then the height is increased step by step. But as the content might overflow this results in an effect that does Not Look Like „slide in“.
All other browsers work as expected.
As a graphic is better than words look at this screencast:
https://www.screencast.com/t/W7aQv2SZK5K
### Reproduction
https://svelte-5-preview.vercel.app/#H4sIAAAAAAAACqVRTUvEMBD9K2MUdheUrh77BSILHsQVPHiwHrLNtIZNk5JMV5bQ_27TUPcHeJuZN_Pe441njVToWPrpmeYdspQ99j27ZXTuQ-NOqAin3pnB1mGSC3kqK12Rv5YNmB41ijH0FQUoVhWR5dpJkkanTkmBhfcgBsvnCTxst1sYx2XZ0VlhUbGO21ZO8D12GRx4fWytGbS4q40yNgUl229qjRKorRFnVMr8ZBWLLOVCNht8DiB8GKtEniyO_4deap_IZvK-DPLDQGQ0GF0rWR8Lv95AUcI6ZgMFXMVqM5b7t91r8vSyf9_lSbwKhDp3tZU9geK6nWIgV7FZSHa9sQQe5ghhhMaaDlbxKckl4lUWthUS_GneOOKE64Yrh5ssmI0aE-_0zc4I2UgULCU74Pg1_gJaN3c8CAIAAA==
### System Info
```shell
System:
OS: Windows 11 10.0.22631
CPU: (8) x64 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Memory: 7.03 GB / 31.75 GB
Binaries:
Node: 20.17.0 - C:\Program Files\nodejs\node.EXE
Yarn: 1.22.17 - ~\AppData\Roaming\npm\yarn.CMD
npm: 10.8.2 - C:\Program Files\nodejs\npm.CMD
pnpm: 9.11.0 - C:\Program Files\nodejs\pnpm.CMD
Browsers:
Edge: Chromium (127.0.2651.74)
Internet Explorer: 11.0.22621.3527
```
### Severity
blocking an upgrade | transition/animation | low | Critical |
2,555,255,736 | yt-dlp | Requesting Suppor for Chapman University Archive video downloads | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm reporting a new site support request
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've checked that none of provided URLs [violate any copyrights](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-website-primarily-used-for-piracy) or contain any [DRM](https://en.wikipedia.org/wiki/Digital_rights_management) to the best of my knowledge
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [X] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and am willing to share it if required
### Region
United States
### Example URLs
- Video Listings: https://blogs.chapman.edu/huell-howser-archives/archives/
- Video Page: https://blogs.chapman.edu/huell-howser-archives/1991/01/10/preserving-the-past-californias-gold-207/
- Single Video Link: https://video.chapman.edu/V/Video?v=9842745&node=43207828&a=103486387&preload=false
### Provide a description that is worded well enough to be understood
Requesting added support for the Chapman University video archives. I belive it's an HLS stream but I am not too sure.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [X] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
C:\Windows\System32>yt-dlp -vU --force-generic-extractor https://video.chapman.edu/V/Video?v=9842745&node=43207828&a=103486387&preload=false -vU
[debug] Command-line config: ['-vU', '--force-generic-extractor', 'https://video.chapman.edu/V/Video?v=9842745']
[debug] Encodings: locale cp1252, fs utf-8, pref cp1252, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version stable@2024.08.06 from yt-dlp/yt-dlp [4d9231208] (pip)
[debug] Python 3.12.3 (CPython AMD64 64bit) - Windows-11-10.0.22631-SP0 (OpenSSL 3.0.13 30 Jan 2024)
[debug] exe versions: ffmpeg N-116328-gfa5a605542-20240718 (setts), ffprobe N-116328-gfa5a605542-20240718, phantomjs 2.1.1
[debug] Optional libraries: Cryptodome-3.20.0, brotli-1.1.0, certifi-2024.07.04, mutagen-1.47.0, requests-2.32.3, sqlite3-3.45.1, urllib3-2.2.2, websockets-12.0
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets
[debug] Loaded 1830 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
[debug] Downloading _update_spec from https://github.com/yt-dlp/yt-dlp/releases/latest/download/_update_spec
Current version: stable@2024.08.06 from yt-dlp/yt-dlp
Latest version: stable@2024.09.27 from yt-dlp/yt-dlp
ERROR: You installed yt-dlp with pip or using the wheel from PyPi; Use that to update
[generic] Extracting URL: https://video.chapman.edu/V/Video?v=9842745
[generic] Video?v=9842745: Downloading webpage
WARNING: [generic] Forcing generic information extractor
[generic] Video?v=9842745: Extracting information
[debug] Looking for embeds
ERROR: Unsupported URL: https://video.chapman.edu/V/Video?v=9842745
Traceback (most recent call last):
File "C:\Python312\Lib\site-packages\yt_dlp\YoutubeDL.py", line 1626, in wrapper
return func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python312\Lib\site-packages\yt_dlp\YoutubeDL.py", line 1761, in __extract_info
ie_result = ie.extract(url)
^^^^^^^^^^^^^^^
File "C:\Python312\Lib\site-packages\yt_dlp\extractor\common.py", line 740, in extract
ie_result = self._real_extract(url)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python312\Lib\site-packages\yt_dlp\extractor\generic.py", line 2526, in _real_extract
raise UnsupportedError(url)
yt_dlp.utils.UnsupportedError: Unsupported URL: https://video.chapman.edu/V/Video?v=9842745
node:internal/modules/cjs/loader:1148
throw err;
^
Error: Cannot find module 'C:\Windows\System32\=43207828'
at Module._resolveFilename (node:internal/modules/cjs/loader:1145:15)
at Module._load (node:internal/modules/cjs/loader:986:27)
at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:174:12)
at node:internal/main/run_main_module:28:49 {
code: 'MODULE_NOT_FOUND',
requireStack: []
}
Node.js v20.13.1
'a' is not recognized as an internal or external command,
operable program or batch file.
'preload' is not recognized as an internal or external command,
operable program or batch file.
```
| site-request,triage | low | Critical |
2,555,287,891 | PowerToys | Keyboard manager broke down after latest update | ### Microsoft PowerToys version
0.84.1
### Installation method
PowerToys auto-update
### Running as admin
Yes
### Area(s) with issue?
Keyboard Manager
### Steps to reproduce
[PowerToysReport_2024-09-29-21-27-26.zip](https://github.com/user-attachments/files/17182358/PowerToysReport_2024-09-29-21-27-26.zip)
I'm not entirely sure if this is what caused it, but after installing the last update, I try to use a shortcut I had previously set up that worked just fine and it worked once before edge started using its default shortcut for that key combination that i didn't even know was a thing because I always used the shortcut I made. In the moment I had ctrl + NumPad1 and ctrl + NumPad3 assigned to send the text ">" and "<", respectively. I tried on other apps besides edge and it still didn't work at all.
### ✔️ Expected Behavior
I was expecting for the shortcuts that I had already and used to work well to keep working.
### ❌ Actual Behavior
None of the shortcuts I tried making nor the key rebindings worked after that, except for one or two, but for some reason the expected output of the latest shortcut was that of the prior shortcut, even when all prior shortcuts were deleted.
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,555,304,960 | yt-dlp | [youtube] 120-hour limit, imposed on live streams is wrong | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm requesting a feature unrelated to a specific site
- [X] I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
### Provide a description that is worded well enough to be understood
Please, make it at least 168 hours or do some actual probing for available timestamps. This hard limit is definitely not flexible and not everyone could patch their youtube.py, especially, Windows users.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [ ] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
[debug] Command-line config: ['-vU']
Deprecated Feature: Support for Windows 7/Server 2008 R2 has been deprecated. See https://github.com/yt-dlp/yt-dlp/issues/10086
for details.
You may stop receiving updates on this version at any time!
[debug] Encodings: locale cp1251, fs utf-8, pref cp1251, out utf-8 (No VT), error utf-8 (No VT), screen utf-8 (No VT)
[debug] yt-dlp version nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds [6328e2e67] (win_exe)
[debug] Python 3.8.10 (CPython AMD64 64bit) - Windows-7-6.1.7601-SP1 (OpenSSL 1.1.1k 25 Mar 2021)
[debug] exe versions: ffmpeg git-2024-09-22-a577d31-ffmpeg-windows-build-helpers (fdk,setts), ffprobe git-2024-09-22-a577d31-ffm
peg-windows-build-helpers
[debug] Optional libraries: Cryptodome-3.20.0, brotli-1.1.0, certifi-2024.08.30, curl_cffi-0.5.10, mutagen-1.47.0, requests-2.32
.3, sqlite3-3.35.5, urllib3-2.2.3, websockets-13.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets, curl_cffi
[debug] Loaded 1838 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp-nightly-builds/releases/latest
Latest version: nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds
yt-dlp is up to date (nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds)
```
| site-enhancement,triage | low | Critical |
2,555,332,481 | go | proposal: slices: funcs `CollectKeys` and `CollectValues` to collect from an iter.Seq2 | ### Proposal Details
The `slices` package currently has `Collect()` to perform `iter.Seq[T] -> []T`, but it doesn't have similar helper functions for collecting the keys or values from an `iter.Seq2[K, V]`.
I propose to add the following two functions to `slices`:
```go
func CollectKeys[K, V any](seq iter.Seq2[K, V]) []K {
var s []K
for k := range seq {
s = append(s, k)
}
return s
}
func CollectValues[K, V any](seq iter.Seq2[K, V]) []V {
var s []V
for _, v := range seq {
s = append(s, v)
}
return s
}
``` | Proposal | low | Minor |
2,555,338,958 | PowerToys | Workspaces error on streamdeck | ### Microsoft PowerToys version
0.84.1
### Installation method
Microsoft Store
### Running as admin
Yes
### Area(s) with issue?
Workspaces
### Steps to reproduce
Hi everyone, I created a workspace and created a shortcut icon on the desktop, when I try to add that file to my streamdeck and try to run that file it gives me this error: Incorrect command line arguments
if I run the file with a double mouse click it works, why doesn't it work when I try to use the same file but via streamdeck? Is it possible to solve it? It's easier for me to manage the workspaces via streamdeck.
thanks
### ✔️ Expected Behavior
_No response_
### ❌ Actual Behavior
_No response_
### Other Software
_No response_ | Issue-Bug,Needs-Triage,Product-Workspaces | low | Critical |
2,555,361,878 | ollama | Error: llama runner process has terminated: error loading modelvocabulary: cannot find tokenizer merges in model file | ### What is the issue?
time : 09/30/2024
script:
```
FROM "./model-quant.gguf"
TEMPLATE """{{- if .System }}
<|im_start|>system {{ .System }}<|im_end|>
{{- end }}
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
SYSTEM """"""
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
```
The creation was successful, but the operation failed
### OS
Linux
### GPU
Nvidia
### CPU
Intel
### Ollama version
ollama version is 0.3.12 | bug | low | Critical |
2,555,424,736 | rust | access outside the bounds for given AllocRange | <!--
Thank you for finding an Internal Compiler Error! 🧊 If possible, try to provide
a minimal verifiable example. You can read "Rust Bug Minimization Patterns" for
how to create smaller examples.
http://blog.pnkfx.org/blog/2019/11/18/rust-bug-minimization-patterns/
-->
### Code
```Rust
#![feature(generic_const_exprs, generic_arg_infer, generic_const_items, associated_const_equality, adt_const_params)]
#![allow(incomplete_features)]
fn foo<const N: usize, const M: usize>(_: [(); N + 1 + M]) {}
#![a]
trait Owner {
const C<const N: u32>: u32;
}
impl Owner for () {
const C<const N: u32>: u32 = N;
}
fn take0<const N: usize>(_: impl Owner<C<N> = { N }>) {}
fn main() {
take0::<128>(());
}
```
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.83.0-nightly (7608018cb 2024-09-29)
binary: rustc
commit-hash: 7608018cbdac9e55d0d13529cf43adc33d53efcf
commit-date: 2024-09-29
host: x86_64-apple-darwin
release: 1.83.0-nightly
LLVM version: 19.1.0
```
### Error output
```
error: an inner attribute is not permitted in this context
--> ./9A756-1.rs:11:1
|
11 | #![this_just_works]
| ^^^^^^^^^^^^^^^^^^^
12 |
13 | / trait Owner {
14 | | const C<const N: u32>: u32;
15 | | }
| |_- the inner attribute doesn't annotate this trait
|
= note: inner attributes, like `#![no_std]`, annotate the item enclosing them, and are usually found at the beginning of source files
error: the constant `N` is not of type `u32`
--> ./9A756-1.rs:21:40
|
21 | fn take0<const N: usize>(_: impl Owner<C<N> = { N }>) {}
| ^^^^^^^^^^^^ expected `u32`, found `usize`
|
note: required by a const generic parameter in `Owner::C`
--> ./9A756-1.rs:14:13
|
14 | const C<const N: u32>: u32;
| ^^^^^^^^^^^^ required by this const generic parameter in `Owner::C`
```
<!--
Include a backtrace in the code block by setting `RUST_BACKTRACE=1` in your
environment. E.g. `RUST_BACKTRACE=1 cargo build`.
-->
<details><summary><strong>Backtrace</strong></summary>
<p>
```
thread 'rustc' panicked at /rustc/7608018cbdac9e55d0d13529cf43adc33d53efcf/compiler/rustc_middle/src/mir/interpret/allocation.rs:268:9:
access outside the bounds for given AllocRange
stack backtrace:
0: 0x10d3193e7 - std::backtrace::Backtrace::create::h697070a74b47c5a1
1: 0x10d319335 - std::backtrace::Backtrace::force_capture::hd4e20dc44637c239
2: 0x10b13a7ce - std[a533c313b02b6cfe]::panicking::update_hook::<alloc[3194a7a73d70d243]::boxed::Box<rustc_driver_impl[e0e0c21a20d76ec4]::install_ice_hook::{closure#0}>>::{closure#0}
3: 0x10d334af8 - std::panicking::rust_panic_with_hook::h9b093984c0b2ae3e
4: 0x10d334735 - std::panicking::begin_panic_handler::{{closure}}::h350248c9538498ad
5: 0x10d331f49 - std::sys::backtrace::__rust_end_short_backtrace::h51a3ed22bf72bc03
6: 0x10d3343ac - _rust_begin_unwind
7: 0x10ff4ff8f - core::panicking::panic_fmt::ha29ff0ee788aef57
8: 0x10b001b9f - <rustc_middle[3d266d78c9b198e4]::mir::interpret::allocation::AllocRange>::subrange
9: 0x10b0862dd - <rustc_const_eval[298ced3d0b3bd135]::interpret::memory::AllocRefMut<rustc_middle[3d266d78c9b198e4]::mir::interpret::pointer::CtfeProvenance, ()>>::write_scalar
10: 0x10b097b4a - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::write_immediate_to_mplace_no_validate
11: 0x10b097977 - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::write_immediate_no_validate::<rustc_const_eval[298ced3d0b3bd135]::interpret::place::MPlaceTy>
12: 0x10b0c993b - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::copy_op_no_validate::<rustc_const_eval[298ced3d0b3bd135]::interpret::operand::OpTy, rustc_const_eval[298ced3d0b3bd135]::interpret::place::MPlaceTy>
13: 0x10b0c278b - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::return_from_current_stack_frame
14: 0x10b0a1446 - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::eval_terminator
15: 0x10b0b9cd4 - rustc_const_eval[298ced3d0b3bd135]::const_eval::eval_queries::eval_to_allocation_raw_provider
16: 0x10c980cfc - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>
17: 0x10c93173e - <rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::dynamic_query::{closure#2} as core[907a20686bf8bf7a]::ops::function::FnOnce<(rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt, rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>)>>::call_once
18: 0x10c748579 - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
19: 0x10c9b823c - rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::get_query_non_incr::__rust_end_short_backtrace
20: 0x10afc62a2 - rustc_middle[3d266d78c9b198e4]::query::plumbing::query_get_at::<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>>
21: 0x10b05e831 - rustc_const_eval[298ced3d0b3bd135]::const_eval::valtrees::eval_to_valtree
22: 0x10bae8d03 - <rustc_const_eval[298ced3d0b3bd135]::provide::{closure#0} as core[907a20686bf8bf7a]::ops::function::FnOnce<(rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt, rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>)>>::call_once
23: 0x10c97ee5c - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_valtree::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>
24: 0x10c910a7e - <rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_valtree::dynamic_query::{closure#2} as core[907a20686bf8bf7a]::ops::function::FnOnce<(rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt, rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>)>>::call_once
25: 0x10c748579 - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
26: 0x10c9b946c - rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_valtree::get_query_non_incr::__rust_end_short_backtrace
27: 0x10bf74b88 - rustc_middle[3d266d78c9b198e4]::query::plumbing::query_get_at::<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>>
28: 0x10bf796f3 - <rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt>::const_eval_global_id_for_typeck
29: 0x10bf79028 - <rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt>::const_eval_resolve_for_typeck
30: 0x10b9c469a - <rustc_infer[9b67ab4c7e1e7e36]::infer::InferCtxt>::const_eval_resolve
31: 0x10b9b3c9a - <rustc_infer[9b67ab4c7e1e7e36]::infer::InferCtxt>::try_const_eval_resolve
32: 0x10d0fd1cf - <rustc_trait_selection[1363494f2f4ec6d3]::traits::fulfill::FulfillProcessor as rustc_data_structures[3069d1c4d7b76162]::obligation_forest::ObligationProcessor>::process_obligation::{closure#0}
33: 0x10d0fc596 - <rustc_trait_selection[1363494f2f4ec6d3]::traits::fulfill::FulfillProcessor as rustc_data_structures[3069d1c4d7b76162]::obligation_forest::ObligationProcessor>::process_obligation
34: 0x10b602dfb - <rustc_data_structures[3069d1c4d7b76162]::obligation_forest::ObligationForest<rustc_trait_selection[1363494f2f4ec6d3]::traits::fulfill::PendingPredicateObligation>>::process_obligations::<rustc_trait_selection[1363494f2f4ec6d3]::traits::fulfill::FulfillProcessor>
35: 0x10b714556 - <rustc_trait_selection[1363494f2f4ec6d3]::traits::fulfill::FulfillmentContext<rustc_trait_selection[1363494f2f4ec6d3]::traits::FulfillmentError> as rustc_infer[9b67ab4c7e1e7e36]::traits::engine::TraitEngine<rustc_trait_selection[1363494f2f4ec6d3]::traits::FulfillmentError>>::select_where_possible
36: 0x10b7d18c2 - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_argument_types
37: 0x10b76d5ce - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::confirm_builtin_call
38: 0x10b8802b1 - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_expr_kind
39: 0x10b79c073 - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_expr_with_expectation_and_args
40: 0x10b7e087e - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_block_with_expected
41: 0x10b79c073 - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_expr_with_expectation_and_args
42: 0x10b79e237 - <rustc_hir_typeck[83d45668b9c71bf7]::fn_ctxt::FnCtxt>::check_return_expr
43: 0x10b8661c2 - rustc_hir_typeck[83d45668b9c71bf7]::check::check_fn
44: 0x10b85f9bc - rustc_hir_typeck[83d45668b9c71bf7]::typeck
45: 0x10c982a7a - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::typeck::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 8usize]>>
46: 0x10c7d8f4e - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::VecCache<rustc_span[51e7cf5b04f4660f]::def_id::LocalDefId, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
47: 0x10c9b1bca - rustc_query_impl[75f1704df0e38289]::query_impl::typeck::get_query_non_incr::__rust_end_short_backtrace
48: 0x10b3f209e - <rustc_middle[3d266d78c9b198e4]::hir::map::Map>::par_body_owners::<rustc_hir_analysis[e5ecc290d4e18640]::check_crate::{closure#4}>::{closure#0}
49: 0x10b57345c - rustc_hir_analysis[e5ecc290d4e18640]::check_crate
50: 0x10bb0a187 - rustc_interface[ee26b89eef7e70ed]::passes::run_required_analyses
51: 0x10bb0d170 - rustc_interface[ee26b89eef7e70ed]::passes::analysis
52: 0x10c982aca - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::analysis::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 1usize]>>
53: 0x10c7388ee - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::SingleCache<rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 1usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
54: 0x10c98f177 - rustc_query_impl[75f1704df0e38289]::query_impl::analysis::get_query_non_incr::__rust_end_short_backtrace
55: 0x10b0e3e77 - <rustc_interface[ee26b89eef7e70ed]::queries::QueryResult<&rustc_middle[3d266d78c9b198e4]::ty::context::GlobalCtxt>>::enter::<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}::{closure#1}::{closure#5}>
56: 0x10b14195d - rustc_interface[ee26b89eef7e70ed]::interface::run_compiler::<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}
57: 0x10b12d59c - std[a533c313b02b6cfe]::sys::backtrace::__rust_begin_short_backtrace::<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_with_globals<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_pool_with_globals<rustc_interface[ee26b89eef7e70ed]::interface::run_compiler<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>
58: 0x10b143f1a - <<std[a533c313b02b6cfe]::thread::Builder>::spawn_unchecked_<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_with_globals<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_pool_with_globals<rustc_interface[ee26b89eef7e70ed]::interface::run_compiler<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#1} as core[907a20686bf8bf7a]::ops::function::FnOnce<()>>::call_once::{shim:vtable#0}
59: 0x10d33f95b - std::sys::pal::unix::thread::Thread::new::thread_start::hc5e64771570de417
60: 0x7ff801f5318b - __pthread_start
rustc version: 1.83.0-nightly (7608018cb 2024-09-29)
platform: x86_64-apple-darwin
query stack during panic:
#0 [eval_to_allocation_raw] const-evaluating + checking `<impl at ./9A756-1.rs:17:1: 17:18>::C`
#1 [eval_to_valtree] evaluating type-level constant
#2 [typeck] type-checking `main`
#3 [analysis] running analysis passes on this crate
end of query stack
```
</p>
</details>
### Note
<strong>Ice location:</strong>
https://github.com/rust-lang/rust/blob/7608018cbdac9e55d0d13529cf43adc33d53efcf/compiler/rustc_middle/src/mir/interpret/allocation.rs#L257-L271 | I-ICE,T-compiler,C-bug,S-bug-has-test,F-associated_const_equality,F-generic_const_items | low | Critical |
2,555,431,963 | rust | ICE: `invalid pointer unsizing` &str -> str | <!--
Thank you for finding an Internal Compiler Error! 🧊 If possible, try to provide
a minimal verifiable example. You can read "Rust Bug Minimization Patterns" for
how to create smaller examples.
http://blog.pnkfx.org/blog/2019/11/18/rust-bug-minimization-patterns/
-->
### Code
```Rust
#![feature(coerce_unsized)]
use std::ops;
trait Trait3<A> {}
impl<A> ops::CoerceUnsized<A> for A where A: ?Sized {}
fn main() {
println!("Hello, world!");
}
```
Command: `rustc ./03FC8.rs`
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.83.0-nightly (7608018cb 2024-09-29)
binary: rustc
commit-hash: 7608018cbdac9e55d0d13529cf43adc33d53efcf
commit-date: 2024-09-29
host: x86_64-apple-darwin
release: 1.83.0-nightly
LLVM version: 19.1.0
```
### Error output
```
error[E0210]: type parameter `A` must be used as the type parameter for some local type (e.g., `MyStruct<A>`)
--> ./03FC8.rs:9:6
|
9 | impl<A> ops::CoerceUnsized<A> for A where A: ?Sized {}
| ^ type parameter `A` must be used as the type parameter for some local type
|
= note: implementing a foreign trait is only possible if at least one of the types for which it is implemented is local
= note: only traits defined in the current crate can be implemented for a type parameter
error[E0376]: the trait `CoerceUnsized` may only be implemented for a coercion between structures
--> ./03FC8.rs:9:1
|
9 | impl<A> ops::CoerceUnsized<A> for A where A: ?Sized {}
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
error: internal compiler error: compiler/rustc_const_eval/src/interpret/cast.rs:465:17: invalid pointer unsizing &str -> str
--> ./03FC8.rs:14:14
|
14 | println!("Hello, world!");
| ^^^^^^^^^^^^^^^
```
<!--
Include a backtrace in the code block by setting `RUST_BACKTRACE=1` in your
environment. E.g. `RUST_BACKTRACE=1 cargo build`.
-->
<details><summary><strong>Backtrace</strong></summary>
<p>
```
thread 'rustc' panicked at compiler/rustc_const_eval/src/interpret/cast.rs:465:17:
Box<dyn Any>
stack backtrace:
0: 0x113f193e7 - std::backtrace::Backtrace::create::h697070a74b47c5a1
1: 0x113f19335 - std::backtrace::Backtrace::force_capture::hd4e20dc44637c239
2: 0x111d3a7ce - std[a533c313b02b6cfe]::panicking::update_hook::<alloc[3194a7a73d70d243]::boxed::Box<rustc_driver_impl[e0e0c21a20d76ec4]::install_ice_hook::{closure#0}>>::{closure#0}
3: 0x113f34af8 - std::panicking::rust_panic_with_hook::h9b093984c0b2ae3e
4: 0x111dbb617 - std[a533c313b02b6cfe]::panicking::begin_panic::<rustc_errors[e7c766416e916d12]::ExplicitBug>::{closure#0}
5: 0x111da7139 - std[a533c313b02b6cfe]::sys::backtrace::__rust_end_short_backtrace::<std[a533c313b02b6cfe]::panicking::begin_panic<rustc_errors[e7c766416e916d12]::ExplicitBug>::{closure#0}, !>
6: 0x116bf2f08 - std[a533c313b02b6cfe]::panicking::begin_panic::<rustc_errors[e7c766416e916d12]::ExplicitBug>
7: 0x111dd0806 - <rustc_errors[e7c766416e916d12]::diagnostic::BugAbort as rustc_errors[e7c766416e916d12]::diagnostic::EmissionGuarantee>::emit_producing_guarantee
8: 0x111baecb1 - <rustc_errors[e7c766416e916d12]::DiagCtxtHandle>::span_bug::<rustc_span[51e7cf5b04f4660f]::span_encoding::Span, alloc[3194a7a73d70d243]::string::String>
9: 0x111be2a98 - rustc_middle[3d266d78c9b198e4]::util::bug::opt_span_bug_fmt::<rustc_span[51e7cf5b04f4660f]::span_encoding::Span>::{closure#0}
10: 0x111be2ad7 - rustc_middle[3d266d78c9b198e4]::ty::context::tls::with_opt::<rustc_middle[3d266d78c9b198e4]::util::bug::opt_span_bug_fmt<rustc_span[51e7cf5b04f4660f]::span_encoding::Span>::{closure#0}, !>::{closure#0}
11: 0x111bc9975 - rustc_middle[3d266d78c9b198e4]::ty::context::tls::with_context_opt::<rustc_middle[3d266d78c9b198e4]::ty::context::tls::with_opt<rustc_middle[3d266d78c9b198e4]::util::bug::opt_span_bug_fmt<rustc_span[51e7cf5b04f4660f]::span_encoding::Span>::{closure#0}, !>::{closure#0}, !>
12: 0x116be1932 - rustc_middle[3d266d78c9b198e4]::util::bug::span_bug_fmt::<rustc_span[51e7cf5b04f4660f]::span_encoding::Span>
13: 0x111c6eba7 - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::unsize_into_ptr
14: 0x111c9d0bd - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::machine::CompileTimeMachine>>::eval_statement
15: 0x111cb9c6c - rustc_const_eval[298ced3d0b3bd135]::const_eval::eval_queries::eval_to_allocation_raw_provider
16: 0x113580cfc - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>
17: 0x11353173e - <rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::dynamic_query::{closure#2} as core[907a20686bf8bf7a]::ops::function::FnOnce<(rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt, rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>)>>::call_once
18: 0x113348579 - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
19: 0x1135b823c - rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_allocation_raw::get_query_non_incr::__rust_end_short_backtrace
20: 0x111bc62a2 - rustc_middle[3d266d78c9b198e4]::query::plumbing::query_get_at::<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>>
21: 0x111cb6763 - rustc_const_eval[298ced3d0b3bd135]::const_eval::eval_queries::eval_to_const_value_raw_provider
22: 0x11358141c - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_const_value_raw::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>
23: 0x11353704e - <rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_const_value_raw::dynamic_query::{closure#2} as core[907a20686bf8bf7a]::ops::function::FnOnce<(rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt, rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>)>>::call_once
24: 0x113348579 - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
25: 0x1135b8e2c - rustc_query_impl[75f1704df0e38289]::query_impl::eval_to_const_value_raw::get_query_non_incr::__rust_end_short_backtrace
26: 0x112b74b88 - rustc_middle[3d266d78c9b198e4]::query::plumbing::query_get_at::<rustc_query_system[13e780f7d1d88911]::query::caches::DefaultCache<rustc_middle[3d266d78c9b198e4]::ty::ParamEnvAnd<rustc_middle[3d266d78c9b198e4]::mir::interpret::GlobalId>, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 24usize]>>>
27: 0x112b79563 - <rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt>::const_eval_global_id
28: 0x112b78e50 - <rustc_middle[3d266d78c9b198e4]::ty::context::TyCtxt>::const_eval_resolve
29: 0x112dbf811 - <rustc_const_eval[298ced3d0b3bd135]::interpret::eval_context::InterpCx<rustc_const_eval[298ced3d0b3bd135]::const_eval::dummy_machine::DummyMachine>>::eval_mir_constant::{closure#0}
30: 0x112ec3849 - <rustc_mir_transform[f683d3911b24b415]::known_panics_lint::ConstPropagator>::eval_constant
31: 0x112ec47e6 - <rustc_mir_transform[f683d3911b24b415]::known_panics_lint::ConstPropagator as rustc_middle[3d266d78c9b198e4]::mir::visit::Visitor>::visit_assign
32: 0x112ec9df2 - <rustc_mir_transform[f683d3911b24b415]::known_panics_lint::ConstPropagator as rustc_middle[3d266d78c9b198e4]::mir::visit::Visitor>::visit_basic_block_data
33: 0x112ec41bc - <rustc_mir_transform[f683d3911b24b415]::known_panics_lint::ConstPropagator as rustc_middle[3d266d78c9b198e4]::mir::visit::Visitor>::visit_body
34: 0x112ec0b70 - <rustc_mir_transform[f683d3911b24b415]::known_panics_lint::KnownPanicsLint as rustc_mir_transform[f683d3911b24b415]::pass_manager::MirLint>::run_lint
35: 0x112e652fa - rustc_mir_transform[f683d3911b24b415]::pass_manager::run_passes_inner
36: 0x112f155c9 - rustc_mir_transform[f683d3911b24b415]::run_analysis_to_runtime_passes
37: 0x112f1517a - rustc_mir_transform[f683d3911b24b415]::mir_drops_elaborated_and_const_checked
38: 0x11358265a - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::mir_drops_elaborated_and_const_checked::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 8usize]>>
39: 0x1133d8f4e - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::VecCache<rustc_span[51e7cf5b04f4660f]::def_id::LocalDefId, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
40: 0x1135982ea - rustc_query_impl[75f1704df0e38289]::query_impl::mir_drops_elaborated_and_const_checked::get_query_non_incr::__rust_end_short_backtrace
41: 0x11270ae48 - rustc_interface[ee26b89eef7e70ed]::passes::run_required_analyses
42: 0x11270d170 - rustc_interface[ee26b89eef7e70ed]::passes::analysis
43: 0x113582aca - rustc_query_impl[75f1704df0e38289]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[75f1704df0e38289]::query_impl::analysis::dynamic_query::{closure#2}::{closure#0}, rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 1usize]>>
44: 0x1133388ee - rustc_query_system[13e780f7d1d88911]::query::plumbing::try_execute_query::<rustc_query_impl[75f1704df0e38289]::DynamicConfig<rustc_query_system[13e780f7d1d88911]::query::caches::SingleCache<rustc_middle[3d266d78c9b198e4]::query::erase::Erased<[u8; 1usize]>>, false, false, false>, rustc_query_impl[75f1704df0e38289]::plumbing::QueryCtxt, false>
45: 0x11358f177 - rustc_query_impl[75f1704df0e38289]::query_impl::analysis::get_query_non_incr::__rust_end_short_backtrace
46: 0x111ce3e77 - <rustc_interface[ee26b89eef7e70ed]::queries::QueryResult<&rustc_middle[3d266d78c9b198e4]::ty::context::GlobalCtxt>>::enter::<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}::{closure#1}::{closure#5}>
47: 0x111d4195d - rustc_interface[ee26b89eef7e70ed]::interface::run_compiler::<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}
48: 0x111d2d59c - std[a533c313b02b6cfe]::sys::backtrace::__rust_begin_short_backtrace::<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_with_globals<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_pool_with_globals<rustc_interface[ee26b89eef7e70ed]::interface::run_compiler<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>
49: 0x111d43f1a - <<std[a533c313b02b6cfe]::thread::Builder>::spawn_unchecked_<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_with_globals<rustc_interface[ee26b89eef7e70ed]::util::run_in_thread_pool_with_globals<rustc_interface[ee26b89eef7e70ed]::interface::run_compiler<core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>, rustc_driver_impl[e0e0c21a20d76ec4]::run_compiler::{closure#0}>::{closure#1}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[907a20686bf8bf7a]::result::Result<(), rustc_span[51e7cf5b04f4660f]::ErrorGuaranteed>>::{closure#1} as core[907a20686bf8bf7a]::ops::function::FnOnce<()>>::call_once::{shim:vtable#0}
50: 0x113f3f95b - std::sys::pal::unix::thread::Thread::new::thread_start::hc5e64771570de417
51: 0x7ff801f5318b - __pthread_start
rustc version: 1.83.0-nightly (7608018cb 2024-09-29)
platform: x86_64-apple-darwin
query stack during panic:
#0 [eval_to_allocation_raw] const-evaluating + checking `main::promoted[0]`
#1 [eval_to_const_value_raw] simplifying constant for the type system `main::promoted[0]`
#2 [mir_drops_elaborated_and_const_checked] elaborating drops for `main`
#3 [analysis] running analysis passes on this crate
end of query stack
```
</p>
</details>
### Note
<strong>Ice location: </strong>
https://github.com/rust-lang/rust/blob/7608018cbdac9e55d0d13529cf43adc33d53efcf/compiler/rustc_const_eval/src/interpret/cast.rs#L460-L471
@rustbot label +F-coerce_unsized | I-ICE,T-compiler,C-bug,F-coerce_unsized,S-has-mcve,S-bug-has-test | low | Critical |
2,555,436,830 | godot | Android Editor [4.4.dev2]: Heavy Lag and Glitches during editing mash and mertarial. | ### Tested versions
4.4.dev2
### System information
Android 10 - Godot 4.4.dev2 - Compatibility Renderer
### Issue description
Editor is glitching and lagging too much when editing mash and mertarial in android editor. Need to optimize.
https://github.com/user-attachments/assets/d1e0913f-c4ce-4e77-a4b2-1b932fad1427
| performance | low | Major |
2,555,443,085 | flutter | EnsureVisible does not work going backwards on a CustomScrollView set to primary inheriting from NestedScrollView | ### Steps to reproduce
Steps:
1. Scroll past an item with the global key in the inner scroll view
2. Press the floating action button to navigate to the item with the key ('no')
3. Observe
Notes:
- works fine when primary is set to false on the CustomScrollView
- works fine when there is no content inside of the outer scroll view (headersliverbuilder)
- works fine when you have not scrolled past the item ('no')
### Expected results
Should navigate to the item with the global key ('no')
### Actual results
Navigated to the top of the screen, above the outer scroll view (green box)
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
const String target = 'no';
void main() {
runApp(const MainApp());
}
class MainApp extends StatefulWidget {
const MainApp({super.key});
@override
State<MainApp> createState() => _MainAppState();
}
final GlobalKey<NestedScrollViewState> nestedKey = GlobalKey();
final GlobalKey scrollKey = GlobalKey();
class _MainAppState extends State<MainApp> {
List<String> stuff = [
"hello",
"goodbye",
"whats up",
"howdy",
"no",
"yes",
"maybe",
"possibly",
"likely",
"could be"
];
@override
Widget build(BuildContext context) {
return MaterialApp(
home: Scaffold(
body: NestedScrollView(
key: nestedKey,
headerSliverBuilder: (context, innerBoxScrolled) => <Widget>[
SliverToBoxAdapter(
child: Container(
height: 300,
color: Colors.green,
),
),
],
body: SizedBox(
height: 500,
child: CustomScrollView(primary: true, slivers: [
SliverToBoxAdapter(
child: Column(
children: stuff
.map((e) => GestureDetector(
onTap: () {},
child: SizedBox(
height: 200,
child: ListTile(
key: e == target ? scrollKey : null,
leading: Text(e),
)),
))
.toList(),
),
),
]),
),
),
floatingActionButton: FloatingActionButton(onPressed: () {
if (nestedKey.currentState != null) {
Scrollable.ensureVisible(scrollKey.currentContext!);
}
}),
));
}
}
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[Upload media here]
https://github.com/user-attachments/assets/11db6a74-17fd-421a-9cdf-868918f425b6
</details>
### Logs
Logs: empty
<details open><summary>Logs</summary>
```console
Showing iPhone 16 Pro Max logs:
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
flutter doctor -v
[✓] Flutter (Channel stable, 3.24.3, on macOS 14.5 23F79 darwin-arm64, locale en-AU)
• Flutter version 3.24.3 on channel stable at /Users/**/Desktop/development/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 2663184aa7 (3 weeks ago), 2024-09-11 16:27:48 -0500
• Engine revision 36335019a8
• Dart version 3.5.3
• DevTools version 2.37.3
[✓] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at /Users/**/Library/Android/sdk
• Platform android-35, build-tools 35.0.0
• ANDROID_HOME = /Users/**/Library/Android/sdk
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 17.0.10+0-17.0.10b1087.21-11609105)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 16.0)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16A242d
• CocoaPods version 1.15.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2024.1)
• Android Studio at /Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.10+0-17.0.10b1087.21-11609105)
[✓] VS Code (version 1.93.1)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.96.0
[✓] Connected device (4 available)
• iPhone 16 Pro Max (mobile) • 7EF3EBC3-5032-463D-9189-66B86C4FFF9E • ios •
com.apple.CoreSimulator.SimRuntime.iOS-18-0 (simulator)
• macOS (desktop) • macos • darwin-arm64 • macOS 14.5 23F79 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 14.5 23F79 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 129.0.6668.70
[✓] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
| framework,f: scrolling,has reproducible steps,P2,team-framework,triaged-framework,found in release: 3.24,found in release: 3.26 | low | Minor |
2,555,457,404 | pytorch | torch.set_float32_matmul_precision('medium') slower than regular BF16 matmul | ### 🐛 Describe the bug
According to the docs, setting the torch float32 matmul precision to 'medium' uses BF16 for the internal GEMM with a FP32 accumulator and returns the FP32 accumulator. My benchmark code (see below) says this is slower than rounding from FP32 to BF16 and then doing the matmul in BF16 and returning a BF16 accumulator. Why is this true? Shouldn't both be using the same BF16 tensorcores and the difference is in the accumulator precision? Is the overhead of using a higher precision accumulator *that much*?
Benchmark script:
```
import torch
import time
sizes = [512, 1024, 2048, 4096, 8192, 16384]
iters = 100
print('Regular FP32')
for sz in sizes:
a = torch.randn(sz, sz, device=0)
b = torch.randn(sz, sz, device=0)
total = 0
for i in range(iters):
s = time.time()
c = a @ b
torch.cuda.synchronize()
total += time.time() - s
print(sz, total / iters)
print()
print('FP32 w/BF16 internal matmul')
torch.set_float32_matmul_precision('medium')
for sz in sizes:
a = torch.randn(sz, sz, device=0)
b = torch.randn(sz, sz, device=0)
total = 0
for i in range(iters):
s = time.time()
c = a @ b
torch.cuda.synchronize()
total += time.time() - s
print(sz, total / iters)
print()
print('regular BF16')
for sz in sizes:
a = torch.randn(sz, sz, device=0)
b = torch.randn(sz, sz, device=0)
total = 0
for i in range(iters):
s = time.time()
c = a.to(torch.bfloat16) @ b.to(torch.bfloat16)
torch.cuda.synchronize()
total += time.time() - s
print(sz, total / iters)
```
Output on a H100 SXM:
```
Regular FP32
512 0.0016167497634887696
1024 7.171869277954102e-05
2048 0.0005328941345214843
4096 0.0026724767684936524
8192 0.021244921684265138
16384 0.16401963710784911
FP32 w/BF16 internal matmul
512 0.00036259174346923827
1024 0.00013562202453613282
2048 0.0001180720329284668
4096 0.0004148006439208984
8192 0.0031256651878356933
16384 0.02780592679977417
regular BF16
512 0.0008567142486572266
1024 0.00077117919921875
2048 7.407903671264648e-05
4096 0.00030952930450439453
8192 0.001969149112701416
16384 0.014865560531616211
```
### Versions
```
Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35
Python version: 3.12.4 | packaged by Anaconda, Inc. | (main, Jun 18 2024, 15:12:24) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-94-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version: 535.154.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 176
On-line CPU(s) list: 0-175
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8468V
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 44
Socket(s): 2
Stepping: 8
BogoMIPS: 4800.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 5.5 MiB (176 instances)
L1i cache: 5.5 MiB (176 instances)
L2 cache: 352 MiB (88 instances)
L3 cache: 32 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-87
NUMA node1 CPU(s): 88-175
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Unknown: No mitigations
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; TSX disabled
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] torch==2.4.0
[pip3] triton==3.0.0
[conda] numpy 1.26.4 pypi_0 pypi
[conda] torch 2.4.0 pypi_0 pypi
[conda] triton 3.0.0 pypi_0 pypi
```
cc @msaroufim @ptrblck | module: performance,module: cuda,triaged | low | Critical |
2,555,469,914 | ui | [bug]: Unexpected token < in JSON at position 0 | ### Describe the bug
# Bug Report: Error when adding v0.dev block to shadcn-ui
## Description
When attempting to add a block from v0.dev to a shadcn-ui project, an error occurs during the execution of the `npx shadcn add` command.
## Steps to Reproduce
1. Start in a directory without a `package.json` file
2. Run the command: `npx shadcn add https://MYURL.v0.build/`
3. Follow the prompts to create a new Next.js project
4. The process fails at the "Checking registry" step
## Expected Behavior
The command should successfully add the v0.dev block to the shadcn-ui project.
## Actual Behavior
The process fails with the following error:
```
Something went wrong. Please check the error below for more details.
If the problem persists, please open an issue on GitHub.
Unexpected token < in JSON at position 0
```
## Environment
- Operating System: macOS
- npm version: 10.8.3 (after update)
- Node.js version: v18.18.2
## Additional Information
- The issue persists after updating npm to the latest version (10.8.3)
- The error occurs during the "Checking registry" step
## Possible Cause
The error message "Unexpected token < in JSON at position 0" typically indicates that the response received is not valid JSON. This could be due to:
1. Network issues causing an HTML error page to be returned instead of JSON data
2. The registry endpoint returning an invalid response
3. A problem with the URL or the content at `https://MYURL.v0.build/`
### Affected component/components
Published Blocks in v0
### How to reproduce
1. Start in a directory without a `package.json` file
2. Run the command: `npx shadcn add https://MYURL.v0.build/`
3. Follow the prompts to create a new Next.js project
4. The process fails at the "Checking registry" step
### Codesandbox/StackBlitz link
_No response_
### Logs
_No response_
### System Info
```bash
M2 MacBook Air, 14.6.1 (23G93)
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,555,472,676 | TypeScript | Bug: null can be excluded by !== null in flow before typeof === 'object', but not excluded by predicate function. | ### 🔎 Search Terms
"null", "control flow", "narrowing", "narrow", "exclusion", "object", "typeof"
### 🕗 Version & Regression Information
Potentially, we could expect the behaviors of `if (a === null)` and `if ((v => v !== null)(a))` (inferred as predicate since TS 5.5) should be the same, but it's actually not in specific cases.
If it's combined with `typeof a === 'object'` check in the same flow, first one is correctly omits the null possibility, while second one doesn't.
[<img width="540" alt="image" src="https://github.com/user-attachments/assets/3b3e2417-4912-456d-b2dc-b0dad8dec016">](https://www.typescriptlang.org/play/?ts=5.6.2#code/MYewdgzgLgBAlhAcgVwDapgXhgCgG4BcMyYA1mCAO5gCUWAfDHlptmGqgNwBQA9LzEEwAegH5uoSLABmWXAEMiJclVoMYAb25D4snAhToc8mnQBOAUyjIzYHjrh6oATwAOFkLPkwAhKxgA5CAARgBWFsBQAeZWNnbaQvL2-CLiAL483BLg0DAA5nLGSmQU1HSYjFoOet6sbBwx1rb2Qo64Lu6eMN5+2EFhEVGNcS2CSdopYtwZQA)
- This changed between versions:
- I confirmed that the exclusion in flow can be done since TS4.5. It's not regression, but the new feature seems to have been partially applied.
- TS4.4 https://www.typescriptlang.org/play/?ts=4.4.4#code/MYewdgzgLgBAlhAcgVwDapgXhgCgG4BcMyYA1mCAO5gCURe8EMYaGmAfDA5j86wNwAoAPTCY4mAD0A-INCRYAMyy4AhkRLkqtLJwDegifGU4EKdDlU0aMAE4BTKMltghRuCagBPAA72QyqowAIS8AOQgAEYAVvbAUGE2Dk4ubhKqbqJSsgC+QoJy4NAwAOYqlhpkFNQ2HDAG7iZBPNgs6EmOzq6GEh643n4BMEGh2BExcQkdKd1GGYZZMoJ5QA
- TS4.5 https://www.typescriptlang.org/play/?ts=4.5.5#code/MYewdgzgLgBAlhAcgVwDapgXhgCgG4BcMyYA1mCAO5gCURe8EMYaGmAfDA5j86wNwAoAPTCY4mAD0A-INCRYAMyy4AhkRLkqtLJwDegifGU4EKdDlU0aMAE4BTKMltghRuCagBPAA72QyqowAIS8AOQgAEYAVvbAUGE2Dk4ubhKqbqJSsgC+QoJy4NAwAOYqlhpkFNQ2HDAG7iZBPNgs6EmOzq6GEh643n4BMEGh2BExcQkdKd1GGYZZMoJ5QA
- This changed in commit or PR (not sure for now, sorry)
### ⏯ Playground Link
https://www.typescriptlang.org/play/?ts=5.6.2#code/MYewdgzgLgBAlhAcgVwDapgXhgCgG4BcMyYA1mCAO5gCUWAfDHlptmGqgNwBQA9LzEEwAegH5uoSLABmWXAEMiJclVoMYAb25D4snAhToc8mnQBOAUyjIzYHjrh6oATwAOFkLPkwAhKxgA5CAARgBWFsBQAeZWNnbaQvL2-CLiAL483BLg0DAA5nLGSmQU1HSYjFoOet6sbBwx1rb2Qo64Lu6eMN5+2EFhEVGNcS2CSdopYtwZQA
### 💻 Code
```ts
const isNull = (v: unknown) => v === null;
// ^?
const f = (a: unknown) => {
if (isNull(a)) return;
if (typeof a !== 'object') return;
a;
// ^?
};
const g = (a: unknown) => {
if (a === null) return;
if (typeof a !== 'object') return;
a;
// ^?
};
```
### 🙁 Actual behavior
Last `a` in `f` is inferred as `object | null`.
### 🙂 Expected behavior
Last `a` in `f` would be inferred as `object`.
### Additional information about the issue
Here is important to check `typeof === 'object'` after the check for null, because type narrowing step is formally, `unknown` → `object | null` → `object`. `=== null` alone cannot narrow anything on `unknown`.
[If you swap the if-statements in above, you can see both is inferred as `object`.](https://www.typescriptlang.org/play/?ts=5.6.2#code/MYewdgzgLgBAlhAcgVwDapgXhgCgG4BcMyYA1mCAO5gCUWAfDHlptmGqgNwBQA9LzEEwAegH5uoSLABmWXAEMiJclVoMYAb25D4snFACeABwCmIWfJgBCVjADkIAEYArE8Ch26AJxNRkXsB4dOD0EFHQceRpvX39A7SF5IP4RcQBfHm4JcGgYAHM5SKUyCmo6TEYtYL1DU3MYSxtsBxc3Dxi-AKChEIUWNg4OuO7BJO0UsW4MoA) | Help Wanted,Possible Improvement | low | Critical |
2,555,500,389 | pytorch | pytorch 2.1.2+cu118, RTX 8000, backward show RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. | ### 🐛 Describe the bug
When I want to train qwen2.5-7B-instruct with using deepspeed, it shows the following erre:
```
Traceback (most recent call last):
File "/home/work/ybs/deeplm/LLM/train.py", line 195, in <module>
run_app()
File "/home/work/ybs/deeplm/LLM/train.py", line 180, in run_app
train(
File "/home/work/ybs/deeplm/LLM/train.py", line 125, in train
model.backward(loss)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn
ret_val = func(*args, **kwargs)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/deepspeed/runtime/engine.py", line 1962, in backward
self.optimizer.backward(loss, retain_graph=retain_graph)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/deepspeed/runtime/fp16/fused_optimizer.py", line 335, in backward
scaled_loss.backward(create_graph=create_graph, retain_graph=retain_graph)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/torch/_tensor.py", line 492, in backward
torch.autograd.backward(
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/torch/autograd/__init__.py", line 251, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/torch/autograd/function.py", line 288, in apply
return user_fn(self, *args)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/torch/utils/checkpoint.py", line 288, in backward
torch.autograd.backward(outputs_with_grad, args_with_grad)
File "/root/miniconda3/envs/llm-agent/lib/python3.9/site-packages/torch/autograd/__init__.py", line 251, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
```
The env setting is listed below. I noticed that there was a same issue a year ago, and it was already solved in the last pytorch version. So I am confused why with pytorch 2.1.2+cu118, the error still shows again. Recall: when head_dim > 64, the error shows up, https://github.com/pytorch/pytorch/pull/99105
### Versions
Collecting environment information...
PyTorch version: 2.1.2+cu118
Is debug build: False
CUDA used to build PyTorch: 11.8
ROCM used to build PyTorch: N/A
OS: CentOS Linux 7 (Core) (x86_64)
GCC version: (GCC) 7.1.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.17
Python version: 3.9.19 (main, May 6 2024, 19:43:03) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-4.19.96-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: Quadro RTX 8000
GPU 1: Quadro RTX 8000
GPU 2: Quadro RTX 8000
GPU 3: Quadro RTX 8000
Nvidia driver version: 525.85.05
cuDNN version: Probably one of the following:
/usr/lib64/libcudnn.so.8.9.7
/usr/lib64/libcudnn_adv_infer.so.8.9.7
/usr/lib64/libcudnn_adv_train.so.8.9.7
/usr/lib64/libcudnn_cnn_infer.so.8.9.7
/usr/lib64/libcudnn_cnn_train.so.8.9.7
/usr/lib64/libcudnn_ops_infer.so.8.9.7
/usr/lib64/libcudnn_ops_train.so.8.9.7
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 80
On-line CPU(s) list: 0-79
Thread(s) per core: 2
Core(s) per socket: 20
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz
Stepping: 7
CPU MHz: 1235.479
CPU max MHz: 4000.0000
CPU min MHz: 800.0000
BogoMIPS: 4200.00
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 1024K
L3 cache: 28160K
NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78
NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts pku ospke avx512_vnni md_clear flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] flake8==6.1.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.22.2
[pip3] torch==2.1.2+cu118
[pip3] torchaudio==2.1.2+cu118
[pip3] torchvision==0.16.2+cu118
[pip3] triton==2.1.0
[conda] numpy 1.22.2 pypi_0 pypi
[conda] torch 2.1.2+cu118 pypi_0 pypi
[conda] torchaudio 2.1.2+cu118 pypi_0 pypi
[conda] torchvision 0.16.2+cu118 pypi_0 pypi
[conda] triton 2.1.0 pypi_0 pypi
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @albanD @gqchen @pearu @nikitaved @soulitzer @Varal7 @xmfan @ptrblck @eqy @drisspg @mikaylagawarecki | needs reproduction,module: autograd,module: cuda,triaged,module: sdpa | low | Critical |
2,555,589,469 | yt-dlp | [youtube:tab] Shorts video. More than 100 from the playlist are not downloaded. | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm reporting that yt-dlp is broken on a **supported** site
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/yt-dlp/yt-dlp/wiki/FAQ#video-url-contains-an-ampersand--and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [X] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and I'm willing to share it if required
### Region
_No response_
### Provide a description that is worded well enough to be understood
Shorts video. More than 100 from the playlist are not downloaded.
If you download from the channel, then everything is ok.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [X] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
tube # /usr/local/bin/yt-dlp -Uv --flat-playlist "https://www.youtube.com/playlist?list=PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r"
[debug] Command-line config: ['-Uv', '--flat-playlist', 'https://www.youtube.com/playlist?list=PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r']
[debug] Encodings: locale UTF-8, fs utf-8, pref UTF-8, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version nightly@2024.09.26.232938 from yt-dlp/yt-dlp-nightly-builds [eabb4680f] (pip)
[debug] Python 3.8.17 (CPython x86_64 64bit) - Linux-5.4.17-2136.334.6.1.el8uek.x86_64-x86_64-with-glibc2.2.5 (OpenSSL 1.1.1k FIPS 25 Mar 2021, glibc 2.28)
[debug] exe versions: ffmpeg 4.2.10, ffprobe 4.2.10
[debug] Optional libraries: Cryptodome-3.20.0, brotli-1.1.0, certifi-2024.08.30, mutagen-1.47.0, requests-2.32.3, sqlite3-3.26.0, urllib3-2.2.3, websockets-13.0.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets
[debug] Loaded 1838 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp-nightly-builds/releases/latest
[debug] Downloading _update_spec from https://github.com/yt-dlp/yt-dlp-nightly-builds/releases/latest/download/_update_spec
Current version: nightly@2024.09.26.232938 from yt-dlp/yt-dlp-nightly-builds
Latest version: nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds
ERROR: You installed yt-dlp with pip or using the wheel from PyPi; Use that to update
[youtube:tab] Extracting URL: https://www.youtube.com/playlist?list=PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r: Downloading webpage
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r: Redownloading playlist API JSON with unavailable videos
[download] Downloading playlist: Shortss
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r page 1: Downloading API JSON
WARNING: [youtube:tab] Incomplete data received. Retrying (1/3)...
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r page 1: Downloading API JSON
WARNING: [youtube:tab] Incomplete data received. Retrying (2/3)...
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r page 1: Downloading API JSON
WARNING: [youtube:tab] Incomplete data received. Retrying (3/3)...
[youtube:tab] PL5Ib645yg8L0NO1Lj4Z3jaQJ9yeQOSa2r page 1: Downloading API JSON
WARNING: [youtube:tab] Incomplete data received. Giving up after 3 retries
[youtube:tab] Playlist Shortss: Downloading 100 items of 301
[debug] The information of all playlist entries will be held in memory
[download] Downloading item 1 of 100
[download] Downloading item 2 of 100
...
```
| site-bug,triage,site:youtube | low | Critical |
2,555,605,005 | PowerToys | Multi-Desktop Powertoy FancyZone settings would change from existing settings after rebooting computer | ### Microsoft PowerToys version
0.84.1
### Installation method
GitHub
### Running as admin
None
### Area(s) with issue?
FancyZones
### Steps to reproduce
Multi-Desktop Powertoy FancyZone settings would change from existing settings after rebooting computer
For example
My settings
Multi-Desktop1: Monitor1 = A, Monitor2 = B
Multi-Desktop2: Monitor1 = C, Monitor2 = D
After rebooting
Multi-Desktop1: Monitor1 = one of the default templates, Monitor2 = one of the default templates
Multi-Desktop2: Monitor1 = A, Monitor2 = B
It looks like this. Could you please fix this so that the settings are preserved after a reboot?
### ✔️ Expected Behavior
Keep existing settings
### ❌ Actual Behavior
Different settings
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,555,669,370 | node | Require of cached modules is not working after a while | ### Version
18.20.4
### Platform
```text
Linux b3fb3508-30f0-4ff0-4220-0bc8 5.15.0-117-generic #127-Ubuntu SMP Fri Jul 5 20:13:28 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux
```
### Subsystem
-
### What steps will reproduce the bug?
The issue we face happens as following:
During the runtime of our backend, we happen to need some code extensions which we basically download and save on the disk ( on demand ofc ), and after we got them in place we require them in the code using the filePath that is being returned by the function which does the download & save on disk. [Yes we know thats not safe, but that works for us right now]
Now, after some weeks or days even of the backend running, these demanded files that are can be found in the require.cache ( once we require the file the first time ) are getting somehow lost, or module.exports of that specific module gets lost.
### How often does it reproduce? Is there a required condition?
Usually, we encounter this issue once every two weeks or similar. ( But from what our users report, its not always the same case )
### What is the expected behavior? Why is that the expected behavior?
We expect the require(filePath) to return the actual functions and other things exposed via module.exports.
### What do you see instead?
Instead, we basically see the following:
<img width="1333" alt="image" src="https://github.com/user-attachments/assets/1d2d3080-4160-4ce7-b460-b46f7f59c5b3">
we also tried to see somehow the require(file)'s keys
<img width="650" alt="image" src="https://github.com/user-attachments/assets/091745a1-20d7-4e75-b676-769458217541">
----
The strange thing is, the file is on the disk, and actually has content in it ( even if in the following picture we dont actually see any module.exports, trust me, those are there )
<img width="1685" alt="image" src="https://github.com/user-attachments/assets/06c7c4ac-07d4-4973-ae11-48e281965161">
While debugging, even if the file itself is on the disk, the debugger does not show it:
<img width="900" alt="image" src="https://github.com/user-attachments/assets/d78ed093-0259-4d89-8e57-4e563ceccf28">
----
as for the require.cache here it is:
### Additional information
I have to mention that usually, using delete require.cache(that require) and downloading the file again solves the issue, or just restarting the server itself. | loaders | low | Critical |
2,555,671,814 | kubernetes | add tests for scheduler-perf itself | /sig scheduling
/kind cleanup
[scheduler-perf](https://github.com/kubernetes/kubernetes/tree/master/test/integration/scheduler_perf) has few tests for itself at the moment; we roughly check the behavior with `-tags performance, short` or `-tags integration-test, short`, which could miss some potential issues with it.
scheduler-perf right now serves a crucial role for the scheduler to keep our targets in various metrics, and we're adding more and more features into it. Unless we have proper testing for it, the more features we add into it, the more likely we could break some existing parts without noticing it since the reviewing would get more and more difficult.
So, this issue aims to add tests for it. I guess it also requires some refactoring, especially around [`runWorkload`](https://github.com/kubernetes/kubernetes/blob/1bbe775d5ffb131636193fe0bc15a8fcc0cd6fd6/test/integration/scheduler_perf/scheduler_perf.go#L1270), which is currently huge.
/cc @alculquicondor @macsko @dom4ha | kind/cleanup,sig/scheduling,needs-triage | low | Major |
2,555,686,091 | PowerToys | FancyZones: Set colour/opacity/blur for certain zones/inactive zones | ### Description of the new feature / enhancement
Set either certain zones, or the option for unused zones, to have a colour/opacity/blur level.
E.g., on a wide monitor, you have a large zone in the middle, and one on each side. Right now, the two either side are transparent when not used.
There could be options to:-
1. Not allow the zones on the left and right to be used, and then set their blur/colour/opacity levels.
2. When unused, the zones will blur/go a colour/change their opacity levels, until they are used.
This will allow you to create a "focus" window in the middle, and remove distractions on the left and right.
### Scenario when this would be used?
This will allow you to have focused zones that are used, as the disallowed/unused zones blur/change colour/go more opaque.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,555,872,026 | material-ui | [docs] Icons aren't searchable anymore in Algolia | See https://github.com/mui/material-ui/pull/41330#issuecomment-2323517472
Icons used to be searchable in [v4](https://v4.mui.com/components/material-icons/#material-icons)
But even after [reverting](https://github.com/mui/material-ui/pull/43569) the icons virtualization, they still aren't searchable.
<img width="951" alt="Screenshot 2024-09-30 at 09 54 56" src="https://github.com/user-attachments/assets/76b0b206-423e-4ecc-a757-0eb88845bc7c">
**Search keywords**: | bug 🐛,docs,package: icons,regression,scope: docs-infra | low | Minor |
2,555,889,158 | node | `require.resolve` cannot find module after calling `require.resolve` and installing dependencies | ### Version
v20.17.0
### Platform
```text
Darwin P03694NWF5 23.1.0 Darwin Kernel Version 23.1.0: Mon Oct 9 21:32:11 PDT 2023; root:xnu-10002.41.9~7/RELEASE_ARM64_T6030 arm64
```
### Subsystem
require
### What steps will reproduce the bug?
1. Init an emty project
```
npm init
```
2. Add a package. e.g. lodash
```
npm install lodash
```
3. Execute this script, the `pkg` can be any dependencies that are not installed in the global environment and current project. e.g. rollup
```javascript
const { exec } = require('child_process');
const pkg = 'rollup';
try {
console.log(require.resolve(pkg));
} catch (e) {
console.log(e);
}
const child = exec(
`npm install ${pkg}`,
() => {
console.log(require.resolve(pkg));
}
);
// sync log from child_process to main process
child.stdout?.on('data', (data) => {
process.stdout.write(data);
});
child.stderr?.on('data', (data) => {
process.stderr.write(data);
});
```
The output shows twice `Error: Cannot find module 'rollup'`, the first one is expected; But the second one seems to be a bug.
### How often does it reproduce? Is there a required condition?
Emerge necessarily.
The required condition is the first `require.resolve` call. Without it, the script works fine.
### What is the expected behavior? Why is that the expected behavior?
Output the resolve path correctly after installing the package
### What do you see instead?
```
Error: Cannot find module 'rollup'
Require stack:
- /Users/Documents/test/index.js
at Module._resolveFilename (node:internal/modules/cjs/loader:1225:15)
at Function.resolve (node:internal/modules/helpers:190:19)
at Object.<anonymous> (/Users/Documents/test/index.js:5:23)
at Module._compile (node:internal/modules/cjs/loader:1469:14)
at Module._extensions..js (node:internal/modules/cjs/loader:1548:10)
at Module.load (node:internal/modules/cjs/loader:1288:32)
at Module._load (node:internal/modules/cjs/loader:1104:12)
at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:174:12)
at node:internal/main/run_main_module:28:49 {
code: 'MODULE_NOT_FOUND',
requireStack: [ '/Users/Documents/test/index.js' ]
}
added 3 packages, and audited 5 packages in 1s
found 0 vulnerabilities
node:internal/modules/cjs/loader:1228
throw err;
^
Error: Cannot find module 'rollup'
Require stack:
- /Users/Documents/test/index.js
at Module._resolveFilename (node:internal/modules/cjs/loader:1225:15)
at Function.resolve (node:internal/modules/helpers:190:19)
at /Users/Documents/test/index.js:13:25
at ChildProcess.exithandler (node:child_process:414:7)
at ChildProcess.emit (node:events:519:28)
at maybeClose (node:internal/child_process:1105:16)
at ChildProcess._handle.onexit (node:internal/child_process:305:5) {
code: 'MODULE_NOT_FOUND',
requireStack: [ '/Users/Documents/test/index.js' ]
}
```
### Additional information
_No response_ | loaders,v20.x | low | Critical |
2,555,921,544 | rust | ICE: `expected int of size 8, but got size 1` in `rustc_middle/src/ty/consts/int.rs` with feature `adt_const_params` | <!--
Thank you for finding an Internal Compiler Error! 🧊 If possible, try to provide
a minimal verifiable example. You can read "Rust Bug Minimization Patterns" for
how to create smaller examples.
http://blog.pnkfx.org/blog/2019/11/18/rust-bug-minimization-patterns/
-->
### Code
(manually reduced)
```Rust
#![feature(adt_const_params)]
#![allow(incomplete_features)]
struct ConstBytes<const T: &'static [*mut u8; 3]>;
pub fn main() {
let _: ConstBytes<b"AAA"> = ConstBytes::<b"BBB">;
}
```
<details><summary><strong>Original Code</strong></summary>
<p>
```Rust
//@ revisions: full min
#![cfg_attr(full, feature(adt_const_params))]
#![cfg_attr(full, allow(incomplete_features))]
struct ConstString<const T: &'static str>;
//[min]~^ ERROR
struct ConstBytes<const T: &'static [*mut u8; mem::size_of::<*mut T>() / mem::size_of::<*mut u8>()]>;
//[min]~^ ERROR
pub fn main() {
let _: ConstString<"Hello"> = ConstString::<"Hello">;
let _: ConstString<"Hello"> = None::<std::slice::Iter<()>>; //~ ERROR mismatched types
let _: ConstString<"ℇ㇈↦"> = ConstString::<"ℇ㇈↦">;
let _: ConstString<"ℇ㇈↦"> = ConstString::<"ℇ㇈↥">; //~ ERROR mismatched types
let _: ConstBytes<b"AAA"> = ConstBytes::<{&[0x41, 0x41, 0x41]}>;
let _: ConstBytes<b"AAA"> = ConstBytes::<b"BBB">; //~ ERROR mismatched types
}
// from tests/ui/const-generics/slice-const-param-mismatch.rs
```
</p>
</details>
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.83.0-nightly (7608018cb 2024-09-29)
binary: rustc
commit-hash: 7608018cbdac9e55d0d13529cf43adc33d53efcf
commit-date: 2024-09-29
host: x86_64-apple-darwin
release: 1.83.0-nightly
LLVM version: 19.1.0
```
### Error output
Command: `rustc`
```
error[E0741]: `&'static [*mut u8; 3]` can't be used as a const parameter type
--> r_E364D18BCB8846EE07601029D3F8CBE898970C9D0A44FC6609A112B969C95B8D_2.rs:4:28
|
4 | struct ConstBytes<const T: &'static [*mut u8; 3]>;
| ^^^^^^^^^^^^^^^^^^^^^
error: internal compiler error: compiler/rustc_middle/src/ty/consts/int.rs:263:13: expected int of size 8, but got size 1
```
<!--
Include a backtrace in the code block by setting `RUST_BACKTRACE=1` in your
environment. E.g. `RUST_BACKTRACE=1 cargo build`.
-->
<details><summary><strong>Backtrace</strong></summary>
<p>
```
thread 'rustc' panicked at compiler/rustc_middle/src/ty/consts/int.rs:263:13:
Box<dyn Any>
stack backtrace:
0: std::panicking::begin_panic::<rustc_errors::ExplicitBug>
1: <rustc_errors::diagnostic::BugAbort as rustc_errors::diagnostic::EmissionGuarantee>::emit_producing_guarantee
2: rustc_middle::util::bug::opt_span_bug_fmt::<rustc_span::span_encoding::Span>::{closure#0}
3: rustc_middle::ty::context::tls::with_opt::<rustc_middle::util::bug::opt_span_bug_fmt<rustc_span::span_encoding::Span>::{closure#0}, !>::{closure#0}
4: rustc_middle::ty::context::tls::with_context_opt::<rustc_middle::ty::context::tls::with_opt<rustc_middle::util::bug::opt_span_bug_fmt<rustc_span::span_encoding::Span>::{closure#0}, !>::{closure#0}, !>
5: rustc_middle::util::bug::bug_fmt
6: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const_scalar_int
7: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const_valtree
8: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const
9: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const_valtree
10: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const_valtree
11: <rustc_middle::ty::print::pretty::FmtPrinter as rustc_middle::ty::print::pretty::PrettyPrinter>::pretty_print_const
12: <rustc_middle::ty::consts::Const as core::fmt::Display>::fmt
13: <rustc_trait_selection::error_reporting::TypeErrCtxt>::cmp
14: <rustc_trait_selection::error_reporting::TypeErrCtxt>::values_str
15: <rustc_trait_selection::error_reporting::TypeErrCtxt>::note_type_err
16: <rustc_trait_selection::error_reporting::TypeErrCtxt>::report_and_explain_type_error
17: <rustc_hir_typeck::fn_ctxt::FnCtxt>::demand_coerce_diag
18: <rustc_hir_typeck::fn_ctxt::FnCtxt>::check_decl
19: <rustc_hir_typeck::fn_ctxt::FnCtxt>::check_block_with_expected
20: <rustc_hir_typeck::fn_ctxt::FnCtxt>::check_expr_with_expectation_and_args
21: <rustc_hir_typeck::fn_ctxt::FnCtxt>::check_return_expr
22: rustc_hir_typeck::check::check_fn
23: rustc_hir_typeck::typeck
[... omitted 1 frame ...]
24: <rustc_middle::hir::map::Map>::par_body_owners::<rustc_hir_analysis::check_crate::{closure#4}>::{closure#0}
25: rustc_hir_analysis::check_crate
26: rustc_interface::passes::run_required_analyses
27: rustc_interface::passes::analysis
[... omitted 1 frame ...]
28: <rustc_interface::queries::QueryResult<&rustc_middle::ty::context::GlobalCtxt>>::enter::<core::result::Result<(), rustc_span::ErrorGuaranteed>, rustc_driver_impl::run_compiler::{closure#0}::{closure#1}::{closure#5}>
29: rustc_interface::interface::run_compiler::<core::result::Result<(), rustc_span::ErrorGuaranteed>, rustc_driver_impl::run_compiler::{closure#0}>::{closure#1}
note: Some details are omitted, run with `RUST_BACKTRACE=full` for a verbose backtrace.
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/Volumes/T7/workspace/blackbox icemaker 결과/240926_240401_blackbox_result/rustc-ice-2024-09-30T08_07_24-63216.txt` to your bug report
query stack during panic:
#0 [typeck] type-checking `main`
#1 [analysis] running analysis passes on this crate
end of query stack
error: aborting due to 2 previous errors
For more information about this error, try `rustc --explain E0741`.
```
</p>
</details>
### Note
- ICE location: `compiler/rustc_middle/src/ty/consts/int.rs Line-263`
https://github.com/rust-lang/rust/blob/7608018cbdac9e55d0d13529cf43adc33d53efcf/compiler/rustc_middle/src/ty/consts/int.rs#L261-L265
- #126359 has identical ICE location.
- but this report requires incomplete feature & regression in `nightly-2024-02-15`
@rustbot label +F-adt_const_params
| I-ICE,T-compiler,C-bug,F-adt_const_params,S-bug-has-test | low | Critical |
2,555,946,509 | flutter | Error where possible null is being asserted in rendering paragraph | ### Steps to reproduce
Spam asynchronous redraws of a Text element on macOS by resizing the window
### Expected results
No Error
### Actual results
```
RenderParagraph.text (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/rendering/paragraph.dart:348)
RenderParagraph.debugDescribeChildren (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/rendering/paragraph.dart:1278)
DiagnosticableTreeNode.getChildren (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:2882)
DiagnosticsNode.toJsonMap.<anonymous closure> (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1611)
DiagnosticsNode.toJsonMap (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1652)
DiagnosticsNode.toJsonList.<anonymous closure> (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1677)
MappedListIterable.elementAt (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:425)
ListIterator.moveNext (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:354)
new _GrowableList._ofEfficientLengthIterable (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/growable_array.dart:189)
new _GrowableList.of (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/growable_array.dart:150)
new List.of (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/array_patch.dart:39)
ListIterable.toList (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:224)
DiagnosticsNode.toJsonList (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1678)
DiagnosticsNode.toJsonMap.<anonymous closure> (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1645)
DiagnosticsNode.toJsonMap (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1652)
DiagnosticsNode.toJsonList.<anonymous closure> (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1677)
MappedListIterable.elementAt (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:425)
ListIterator.moveNext (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:354)
new _GrowableList._ofEfficientLengthIterable (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/growable_array.dart:189)
new _GrowableList.of (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/growable_array.dart:150)
new List.of (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/_internal/vm/lib/array_patch.dart:39)
ListIterable.toList (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/bin/cache/pkg/sky_engine/lib/internal/iterable.dart:224)
DiagnosticsNode.toJsonList (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1678)
DiagnosticsNode.toJsonMap.<anonymous closure> (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1639)
DiagnosticsNode.toJsonMap (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/foundation/diagnostics.dart:1652)
WidgetInspectorService._nodeToJson (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/widgets/widget_inspector.dart:1735)
WidgetInspectorService._reportStructuredError (/opt/homebrew/Caskroom/flutter/3.24.3/flutter/packages/flutter/lib/src/widgets/widget_inspector.dart:997)
<asynchronous gap> (Unknown Source:0)
```
### Code sample
This is happening on a "Text" widget that is just `Text("string")`
### Screenshots or Video
N/A
### Logs
N/A
### Flutter Doctor output
```
Doctor summary (to see all details, run flutter doctor -v):
[✓] Flutter (Channel stable, 3.24.3, on macOS 15.0 24A335 darwin-arm64, locale en-NZ)
[!] Android toolchain - develop for Android devices (Android SDK version 33.0.1)
✗ cmdline-tools component is missing
Run `path/to/sdkmanager --install "cmdline-tools;latest"`
See https://developer.android.com/studio/command-line for more details.
✗ Android license status unknown.
Run `flutter doctor --android-licenses` to accept the SDK licenses.
See https://flutter.dev/to/macos-android-setup for more details.
[✓] Xcode - develop for iOS and macOS (Xcode 16.0)
[✓] Chrome - develop for the web
[✓] Android Studio (version 2022.3)
[✓] VS Code (version 1.93.1)
[✓] Connected device (5 available)
[✓] Network resources
! Doctor found issues in 1 category.
``` | framework,a: error message,P2,team-text-input,triaged-text-input | low | Critical |
2,555,964,875 | transformers | Improve image processing time | ### Feature request
Optimize Transformers' image_processors to decrease image processing time, and reduce inference latency for vision models and vlms.
### Motivation
The Transformers library relies on PIL (Pillow) for image preprocessing, which can become a major bottleneck during inference, especially with compiled models where the preprocessing time can dominate the overall inference time.
In the examples above, the RT-DETR preprocessing necessitates only to resize the image, while the DETR one involves resize+normalize.
In eager mode, image preprocessing takes a big part of the total inference time for RT-DETR, but is not the main bottleneck. However, with a compiled RT-DETR, image preprocessing takes up the majority of the inference time, underlining the necessity to optimize it. This is even clearer for DETR, where image preprocessing is already the main bottleneck in eager mode.
However, alternative libraries exist that leverage available hardware more efficiently for faster image preprocessing.
[OptimVision](https://github.com/yonigozlan/OptimVision) uses such libraries to get much better results compared to Transformers.
Much more details on OptimVision and image processing methods comparison are available on this [Notion page](https://www.notion.so/huggingface2/OptimVision-Optimize-preprocessing-time-10f1384ebcac8091a12debb87fe5f591?pvs=4).
### Your contribution
OptimVision is an experiment playground to optimize the different steps involved in inferring/training with vision models.
The current fast image preprocessing in OptimVision is a proof of concept and is not yet ready to be merged into Transformers, but that this the ultimate goal :). | Feature request,Vision,optimization,Processing | low | Major |
2,555,997,664 | PowerToys | Seamless Night Light | ### Description of the new feature / enhancement
Instead of one setting for the night light which often seems too strong/soft at sunset/sunrise time it would be awesome to transition seamlessly and according to the actual daytime.
### Scenario when this would be used?
Every-Day Use and especially for people who tend to work very early or late.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,556,016,964 | ui | [bug]: useFormField can be used without being nested within FormField | ### Describe the bug
useFormField has a check that should prevent it from being used when it is not called within a FormField component.
This error is not thrown because empty objects (the default of the context when it is not wrapped in a provider) are true when checking in the if condition.
### Affected component/components
Form
### How to reproduce
1. Render any component that uses useFormField within a Form without being inside of a FormField component.
2. Don't see the error.
### Codesandbox/StackBlitz link
https://stackblitz.com/edit/vitejs-vite-za3zz1?file=src%2FApp.tsx
### Logs
_No response_
### System Info
```bash
MacOS, Chrome
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,556,030,128 | vscode | Conflict resolver worked not expected when I click accpect incoming or current | Edit from @hediet:
When accepting conflict 1 and 2 fast enough, the edit for conflict 2 does not take into account the (still ongoing) edit for conflict 1.
---
<!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.1 (system setup)
- OS Version: Windows_NT x64 10.0.22631
Steps to Reproduce:
1. Some time I tried to resolve conflict in vscode. It worked ok when there was only on conflict, if two conflict came up, the first one could been resolved smooth by clicking accept incoming or current button. But the second will failed, after clicking one accept button, it didn't work.
2. Then I pressed ctrl+z to undo, and clicked the button again, it worked ok .
| bug,merge-conflict | low | Critical |
2,556,046,195 | PowerToys | new feature | ### Description of the new feature / enhancement
You hold down some button
While you hold the button keyboard layout switches to the selected one
You release the button
The keyboard layout switches to the original one
### Scenario when this would be used?
write very quickly on the Russian keyboard #
for example RightAlt+Shift+3 give us # on the Russian layout
or the № on the English layout switching to Russian
### Supporting information
_No response_ | Idea-Enhancement,Product-Keyboard Shortcut Manager,Needs-Triage | low | Minor |
2,556,094,545 | vscode | Screen reader box incorrectly positioned when selecting multiple lines | The screen reader box incorrectly positioned when selecting multiple lines when using MacOS voice over
This is because the edit context hidden element is incorrectly positioned on multi-line selections
https://github.com/user-attachments/assets/3992fe5b-71ca-4a59-919e-10e27dc9f1ae
| bug,editor-input | low | Minor |
2,556,107,386 | ollama | Warn users when input is longer than supported context | ### What is the issue?
Hi thanks for the great library! It would be great if there could be a warning when input is longer than supported context. Otherwise, if the text is silently truncated, the behavior can be confusing.
### OS
_No response_
### GPU
_No response_
### CPU
_No response_
### Ollama version
_No response_ | bug | low | Minor |
2,556,196,884 | langchain | ModuleNotFoundError: No module named 'rank_llm.rerank.zephyr_reranker' (update of rank_llm.rerank -> rank_llm.rerank.listwise.zephyr_reranker) | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
`from rank_llm.rerank.listwise.zephyr_reranker import ZephyrReranker`
🧨🧨 `from rank_llm.rerank.zephyr_reranker import ZephyrReranker`
### Error Message and Stack Trace (if applicable)
ModuleNotFoundError: No module named 'rank_llm.rerank.zephyr_reranker'
### Description
I think the `rank_llm` updated version changed the package locations:
worked: `from rank_llm.rerank.listwise.zephyr_reranker import ZephyrReranker`
not worked: `from rank_llm.rerank.zephyr_reranker import ZephyrReranker`
### System Info
up2date langchain | 🤖:bug,stale | low | Critical |
2,556,198,362 | PowerToys | Add a Highlight Border When Switching Windows | ### Description of the new feature / enhancement
When working on a large monitor with 3+ windows visible at a time, it can often be confusing to know which window is in focus, or which window you've instantly alt + tabbed to.
My suggestion is to add an feature that adds a 1px blue border (or whatever) that fades out over 2 seconds or so, to whichever window becomes activated. This way, you will instantly know which one you've selected.
Additionally - although a bit different/more technical, I think it could also be really useful to be able to proximity-switch to a window based on FancyZones zones. So basically you can "move" the active zone, which would function just like moving the active window around using hotkeys, except instead of moving the window, you're moving the "active zone", and whichever window was last accessed in the zone you land on, becomes active.
### Scenario when this would be used?
This would be especially useful for large monitors where you quickly want to switch between windows. While the alt+tab windows overview is of course very useful, this requires you to "study" the windows for a second in order to choose the right one - meaning, if you simply quick swap with alt + tab, it's usually almost impossible to know which window you've now switched to, if it's one of the windows that are already visible and for instance, in another FancyZones zone.
Additionally, especially with browsers, you'll often have multiple browsers open with very similar content on them, making it hard to distinguish which one you want.
For instance, let's say you have your editor in one zone, and two github repos open in their own windows in other zones. Visually, on your monitor, you know which window you want to tab to, but with alt + tab, the window previews will look very similar, and I often find myself selecting the wrong window, and having to hit some other key to see which one I'm in (eg. up/down arrow key to see which one scrolls).
I think the border glow would help with this, but switching active zones would be even better.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,556,216,269 | godot | NodePath property targeting breaks when the targets script is overridden in an inherited scene. | ### Tested versions
Tested in 4.4-dev2_mono_win64 and 4.3-stable_mono_win64
### System information
Godot v4.4.dev2.mono - Windows 10.0.22631 - Vulkan (Forward+) - dedicated NVIDIA GeForce RTX 4080 (NVIDIA; 31.0.15.4633) - AMD Ryzen 7 5800X 8-Core Processor (16 Threads)
### Issue description
When the target of an exported NodePath property has its script overridden in an inherited scene, the NodePath breaks and throws a ObjectDisposedException.
### Steps to reproduce
To reproduce this bug, one needs a BaseScene, an InheritedScene (created via "New Inherited Scene" of the BaseScene), a BaseScript, a OtherScript and finally one ScriptWithExport with one export of the type Node.
The BaseScene looks as follows:
BaseScene (BaseScript)
+ScriptWithExport (Exported variable Target targets BaseScene)
The InheritedScene looks like this:
InheritedScene (OtherScript)
+ScriptWithExport (Exported variable Target targets InheritedScene)
Inside the _Ready function of the ScriptWithExport function add one line which prints the Target.
While the BaseScene works as expected, the InheritedScene will throw an ObjectDisposedException. Replacing OtherScript with BaseScript in the Inherited Scene, will result in a working condition again.
The targeted node does not have to be the root node, the same error can be reproduced when any node has its script overridden and is the target of an exported NodePath property.
### Minimal reproduction project (MRP)
[minimal-repro-inheritance.zip](https://github.com/user-attachments/files/17188270/minimal-repro-inheritance.zip)
| bug,topic:editor | low | Critical |
2,556,242,630 | tensorflow | Multithreading is not working with teansorflow | ### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tensorflow==2.15.0.post1
### Custom code
Yes
### OS platform and distribution
_No response_
### Mobile device
_No response_
### Python version
python:3.10.12
### Bazel version
_No response_
### GCC/compiler version
_No response_
### CUDA/cuDNN version
_No response_
### GPU model and memory
_No response_
### Current behavior?
I am using bert model for classification and serving the model with gunicorn worker_class=gthreads, tf.config.threading.set_intra_op_parallelism_threads(1)
tf.config.threading.set_inter_op_parallelism_threads(1)
when I using above two line of code the code is working fine as expected and if increase the number to more than 1, the code getting blocked at the below line of code
# Make predictions
outputs = model_obj(inputs)
and also inorder to reduce the docker image size I am using
RUN pip3 install torch==2.0.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
before installing all the dependencies
Flask==2.2.5
g2p-en==2.1.0
gunicorn==21.2.0
jellyfish==1.0.3
kenlm==0.2.0
nltk==3.8.1
numpy==1.26.3
pandas==2.2.0
python-dotenv==1.0.1
requests==2.31.0
scikit-learn==1.4.0
semantic-router==0.0.17
semantic-router[fastembed]
sentence-transformers==2.3.1
tensorflow==2.15.0.post1
tensorflow-hub==0.16.0
theano==1.0.5
transformers==4.37.2
Werkzeug==2.2.2
please tell me why is my code is getting blocked if I use more than 1 thread.
### Standalone code to reproduce the issue
```shell
def intent_prediction(self, sentence, thresold_score):
logger.info(f"Threshold Score: {thresold_score}")
try:
model_obj = intent_object_dict[self.model]
except KeyError:
logger.error("Model not found in intent_object_dict")
model_obj = self.load_model()
if INTENT_MODEL == "cohere":
score, intent = self.cohere_intent_prediction(sentence, model_obj)
else:
score, intent = self.Bert_intent_prediction(
sentence, model_obj, thresold_score
)
return score, intent
def Bert_intent_prediction(self, sentence, model_obj, thresold_score):
inputs = self.load_BERT_tokenizer(sentence)
# Make predictions
outputs = model_obj(inputs)
# Get predicted class
probabilities = tf.nn.softmax(outputs.logits, axis=1)
predicted_class = tf.argmax(probabilities, axis=1).numpy()[0]
matching_score = probabilities[0][predicted_class].numpy()
try:
intent_data = intent_label_dict[self.model]
except Exception as e:
logger.error(f"error while getting label: {e}")
intent_data = self.get_intent_labels()
if matching_score >= thresold_score:
logger.info(
f"Matched Main Intent:\
{intent_data[predicted_class]},\
SCORE :{matching_score}"
)
logger.info(f"Matched Sentence: {intent_data[predicted_class]}")
else:
logger.info(f"Intent not matched, score is {matching_score}")
intent = intent_data[predicted_class]
return str(matching_score), intent
```
### Relevant log output
```shell
30-Sep-2024 15:50:42.761|INFO |__init__|I want my sofa get cleaned|
__init__.py:171|Enter into PUNC for intent...
30-Sep-2024 15:50:42.761|INFO |phrase_sim|I want my sofa get cleaned|
phrase_sim.py:72|Threshold Score: 0.7
after this the code is blocked
```
| stat:awaiting tensorflower,type:bug,TF 2.15 | low | Critical |
2,556,259,842 | PowerToys | Different Results in OpenAI Playground vs requests sent to API from Advanced Paste | ### Microsoft PowerToys version
0.84.1
### Installation method
Microsoft Store
### Running as admin
No
### Area(s) with issue?
Advanced Paste
### Steps to reproduce
Adding a custom action with very specific prompt gives a wrong result, where trying the same prompt in Playground gives the correct result. Using gpt-3.5-turbo in Playground so it is the same as Advanced paste.
Example prompt:
"0099-0ac8-0084"
Strip dividers ":", "-", ".". Strip "0099". Divide to 4 octets with dots. Convert octets to dec.
### ✔️ Expected Behavior
10.200.0.132
### ❌ Actual Behavior
172.200.0.132
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,556,347,611 | react | Inability to prioritise hydration & react yields too willingly | # Summary
React does not provide an API to set the priority on a component or suspense boundary for hydration. This means you cannot optimise your application to hydrate part of the app you know users will want to interact with first. Or in my case a part of the application I need to start rendering client side asap to replace a SSR skeleton with the correct personalised content that can only be rendered client side.
The issue is compounded by the way React 18 yields the main thread during hydration to other higher priority events, which while a great idea in theory to improve FID and INP, in practice means 3rd party loaded (gtm) scripts delay the initial hydrating. It would be great if this logic could differentiate between user interactions and scripts added to the call stack?
Detailed here https://github.com/reactwg/react-18/discussions/38#discussioncomment-837161
My real-world use case is an ecommerce application where marketing teams are loading via gtm vast amounts of 3rd party scripts, think tiktok, instagram, bing, and masses of gtm containers. While the ideal solution would be to either trim these down or move them to the worker threads via something like partytown (https://partytown.builder.io/), neither is realistic. As such we need a way to optimise around them.
We can see, on slower windows machines and older mobiles, initial hydration of components take more than 5-8 seconds to start. This provides a negative experience to customers where skeletons are visible, and a worse UX than the legacy MVC sites.
##Work arounds
As detailed here there are potential workarounds that already exist
https://github.com/reactwg/react-18/discussions/130
Firstly the `unstable_scheduleHydration` API, however this has since been moved to the hydrateRoot function and is no longer accessible in Next.js (I believe?) (https://github.com/facebook/react/pull/22455/files)
The second, and this is where you have to forgive me, is to creatively interpret the following
` Discrete events (eg. click/keypresses) trigger synchronous (selective) hydration in the capture phase if the code in its encapsulating Suspense boundary is ready.
If the event can't be synchronously hydrated then we'll increase the priority of that boundary so it hydrates first when it's ready.`
Which leads to this being an incredible performance optimisation
```
useEffect(() => {
document.getElementById("body")?.click();
}, []);
```
Because React batches hydration together at Suspense layers, it does an initial render down to the Suspense boundary, then processes the useLayoutEffects, then useEffects, then finally starts the child boundary. This logic when applied in the parent and clicking an element in the first child boundary, forces React into a synchronous render, no longer yielding, and prioritising above all other suspense boundaries the one you clicked.
## Evidence
Reproducible example here https://github.com/edqwerty1/hydrate
Visit http://localhost:3000/slow for no click logic, and http://localhost:3000/fast for the improved version.
In this scenario I really need Content Right to hydrate first as I must replace a SSR skeleton with my personalised content
### Before
<img width="345" alt="image" src="https://github.com/user-attachments/assets/1410a856-e8c8-4bbc-974c-0d573666e0c2">
It is delayed by around 5 seconds, these timings are realistic to real world data. The gtm scripts don’t normally block for an entire second, but there are normally a lot more of them.
### After
<img width="342" alt="image" src="https://github.com/user-attachments/assets/446cfd41-2977-4fe9-bc7e-4c08ca0959b0">
Content Right hydrated in 2.5s, half the time. And more importantly the time between App starting and my component rendering has reduced from 2.3s to 200ms! A very large saving and if I reorder the initial script tags I could in theory delay the 3rd party code until my entire app is ready.
Now this of course isn't idea, by hacking the hydration logic I am potentially causing higher INP scores for real events, and there may be other issues.
| Type: Discussion | medium | Major |
2,556,369,243 | svelte | Own TS types for types of input elements | ### Describe the problem
Now there is only a single type [HTMLInputAttributes](https://github.com/sveltejs/svelte/blob/svelte%405.0.0-next.260/packages/svelte/elements.d.ts#L1036) for all input elements and there is e.g. the library `flowbite-svelte` which uses this type to [extend](https://github.com/sveltejs/svelte/blob/svelte%405.0.0-next.260/packages/svelte/elements.d.ts#L1036) the props of a component with it. The advantage is that the maintainers don't have to implement each prop themselves but it comes with the disadvantage that the component has more props than it should have.
### Describe the proposed solution
It would be nice to have types like for example `HTMLInputRadioAttributes` which are specific for one type of input element. Then libraries could extend the props of their components with these types.
### Importance
nice to have | types / typescript | low | Minor |
2,556,395,386 | langchain | ChatDatabricks() unable to stream special characters | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
## Config rag_chain_config.yaml
```yml
databricks_resources:
llm_endpoint_name: gpt-4o-mini
vector_search_endpoint_name: VS_ENDPOINT
input_example:
messages:
- content: Hvilken vinterrug sort havde mest udbytte i 2023?
role: user
- content: Det største udbytte i årets landsforsøg med sorter af vinterrug i 2023
var 112,1 hkg pr. ha, og det blev høstet i sorten KWS Cursor.
role: assistant
- content: Hvilken vinterhvede sort havde mest udbytte i 2023?
role: user
llm_config:
llm_parameters:
max_tokens: 1500
temperature: 0.01
llm_system_prompt_template: "\n You are a trusted assistant that helps answer\
\ questions based only on the provided information. If you do not know the answer\
\ to a question, you truthfully say you do not know. Here is some context which\
\ might or might not help you answer: {context}. Answer directly, do not repeat\
\ the question, do not start with something like: the answer to the question,\
\ do not add AI in front of your answer, do not say: here is the answer, do not\
\ mention the context or the question. You must provide your answer in the Danish\
\ language or in the detected language if the queried question from the user differs\
\ from Danish.\n If the answer contains multiple steps or points, provide the\
\ answer in a bullet format. \n Based on this context, answer this question:\
\ {question}\n"
retriever_config:
chunk_template: 'Passage: {chunk_text}
'
data_pipeline_tag: poc
parameters:
k: 5
query_type: hybrid
schema:
chunk_text: chunked_text
document_uri: path
primary_key: chunk_id
vector_search_index: VS_INDEX
```
## Code example
```python
from operator import itemgetter
import mlflow
import os
from databricks.vector_search.client import VectorSearchClient
from langchain_community.chat_models import ChatDatabricks
from langchain_community.vectorstores import DatabricksVectorSearch
from langchain_core.runnables import RunnableLambda
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import (
PromptTemplate,
ChatPromptTemplate,
)
## Enable MLflow Tracing
mlflow.langchain.autolog()
############
# Helper functions
############
# Return the string contents of the most recent message from the user
def extract_user_query_string(chat_messages_array):
return chat_messages_array[-1]["content"]
# Return the chat history, which is is everything before the last question
def extract_chat_history(chat_messages_array):
return chat_messages_array[:-1]
# FIT AND FINISH: We should not require a value here.
model_config = mlflow.models.ModelConfig(development_config='rag_chain_config.yaml')
databricks_resources = model_config.get("databricks_resources")
retriever_config = model_config.get("retriever_config")
llm_config = model_config.get("llm_config")
############
# Connect to the Vector Search Index
############
vs_client = VectorSearchClient(disable_notice=True)
vs_index = vs_client.get_index(
endpoint_name=databricks_resources.get("vector_search_endpoint_name"),
index_name=retriever_config.get("vector_search_index"),
)
vector_search_schema = retriever_config.get("schema")
############
# Turn the Vector Search index into a LangChain retriever
############
vector_search_as_retriever = DatabricksVectorSearch(
vs_index,
text_column=vector_search_schema.get("chunk_text"),
columns=[
vector_search_schema.get("primary_key"),
vector_search_schema.get("chunk_text"),
vector_search_schema.get("document_uri"),
],
).as_retriever(search_kwargs=retriever_config.get("parameters"))
############
# Required to:
# 1. Enable the RAG Studio Review App to properly display retrieved chunks
# 2. Enable evaluation suite to measure the retriever
############
mlflow.models.set_retriever_schema(
primary_key=vector_search_schema.get("primary_key"),
text_column=vector_search_schema.get("chunk_text"),
doc_uri=vector_search_schema.get(
"document_uri"
), # Review App uses `doc_uri` to display chunks from the same document in a single view
)
############
# Method to format the docs returned by the retriever into the prompt
############
def format_context(docs):
chunk_template = retriever_config.get("chunk_template")
chunk_contents = [
chunk_template.format(
chunk_text=d.page_content,
document_uri=d.metadata[vector_search_schema.get("document_uri")],
)
for d in docs
]
return "".join(chunk_contents)
############
# Prompt Template for generation
############
prompt = ChatPromptTemplate.from_messages(
[
( # System prompt contains the instructions
"system",
llm_config.get("llm_system_prompt_template"),
),
# User's question
("user", "{question}"),
]
)
############
# FM for generation
############
model = ChatDatabricks(
endpoint=databricks_resources.get("llm_endpoint_name"),
extra_params=llm_config.get("llm_parameters")
)
############
# RAG Chain
############
chain = (
{
"question": itemgetter("messages") | RunnableLambda(extract_user_query_string),
"context": itemgetter("messages")
| RunnableLambda(extract_user_query_string)
| vector_search_as_retriever
| RunnableLambda(format_context),
}
| prompt
| model
| StrOutputParser()
)
## Tell MLflow logging where to find your chain.
# `mlflow.models.set_model(model=...)` function specifies the LangChain chain to use for evaluation and deployment. This is required to log this chain to MLflow with `mlflow.langchain.log_model(...)`.
mlflow.models.set_model(model=chain)
# Streaming example output
chain_input = {
"messages": [
{
"role": "user",
"content": "Hvordan bekæmper man væselhale?",
}
]
}
for chunk in chain.stream(chain_input):
print(chunk, end="|", flush=True)
```
### Error Message and Stack Trace (if applicable)
## Code example streams the following strange formatting of special Danish characters "æ, ø, å":
```
|-| Bek|æ|mp|else| skal| ske| så| tid|ligt| som| muligt| efter| frem|spiring|.
|-| An|vend|else| af| M|aten|o| Duo| |600| SC| er| effektiv|,| især| ved| tid|lig| behandling|.
|-| Be|handling| med| |0|,|7| l| M|aten|o| Duo| pr|.| ha| den| |20|.| august| har| g|ivet| de| bedste| result|ater|.
|-| T|ils|æt|ning| af| Boxer| kan| forbed|re| bek|æ|mp|elsen|,| men| kan| være| problem|at|isk| på| grund| af| ford|amp|ning|.
|-| Det| er| vigtigt| at| reduc|ere| væ|sel|hale| til| et| niveau|,| hvor| de| ikke| påvir|ker| op|form|ering| og| sp|red|ning|.||
```
However, when manually correcting the output:
```python
for chunk in chain.stream(chain_input):
# Decode using latin1 (or the incorrect encoding) and re-encode in UTF-8
corrected_chunk = chunk.encode('latin1').decode('utf-8')
print(corrected_chunk, end="|", flush=True)
```
```
|-| Bek|æ|mp|else| skal| ske| så| tid|ligt| som| muligt| efter| frem|spiring|.
|-| An|vend|else| af| M|aten|o| Duo| |600| SC| er| effektiv|,| især| ved| tid|lig| behandling|.
|-| Be|handling| med| |0|,|7| l| M|aten|o| Duo| pr|.| ha| den| |20|.| august| har| vist| sig| at| være| den| bedste| metode|.
|-| T|ils|æt|ning| af| Boxer| kan| forbed|re| bek|æ|mp|elsen|,| men| kan| være| problem|at|isk| at| anv|ende| tid|ligt| på| grund| af| ford|amp|ning|.
|-| Det| er| vigtigt| at| reduc|ere| væ|sel|hale| til| et| niveau|,| hvor| de| ikke| påvir|ker| op|form|ering| og| sp|red|ning|.||
```
## Error clearly happens in ChatDatabricks()
## Workaround is currently to turn off streaming
```python
model = ChatDatabricks(
endpoint=databricks_resources.get("llm_endpoint_name"),
extra_params=llm_config.get("llm_parameters"),
disable_streaming=True
)
```
### Description
from langchain_community.chat_models import ChatDatabricks unable to stream special Danish characters.
I expect to see "æ", "ø" and "å".
Instead I see strange representations formatted like: "æt" and "å"
### System Info
anyio==3.5.0
argon2-cffi==21.3.0
argon2-cffi-bindings==21.2.0
asttokens==2.0.5
attrs==22.1.0
backcall==0.2.0
beautifulsoup4==4.11.1
black==22.6.0
bleach==4.1.0
blinker==1.4
boto3==1.24.28
botocore==1.27.96
certifi==2022.12.7
cffi==1.15.1
chardet==4.0.0
charset-normalizer==2.0.4
click==8.0.4
comm==0.1.2
contourpy==1.0.5
cryptography==39.0.1
cycler==0.11.0
Cython==0.29.32
databricks-sdk==0.1.6
dbus-python==1.2.18
debugpy==1.6.7
decorator==5.1.1
defusedxml==0.7.1
distlib==0.3.7
distro==1.7.0
distro-info==1.1+ubuntu0.2
docstring-to-markdown==0.11
entrypoints==0.4
executing==0.8.3
facets-overview==1.1.1
fastjsonschema==2.19.1
filelock==3.13.1
fonttools==4.25.0
googleapis-common-protos==1.62.0
grpcio==1.48.2
grpcio-status==1.48.1
httplib2==0.20.2
idna==3.4
importlib-metadata==4.6.4
ipykernel==6.25.0
ipython==8.14.0
ipython-genutils==0.2.0
ipywidgets==7.7.2
jedi==0.18.1
jeepney==0.7.1
Jinja2==3.1.2
jmespath==0.10.0
joblib==1.2.0
jsonschema==4.17.3
jupyter-client==7.3.4
jupyter-server==1.23.4
jupyter_core==5.2.0
jupyterlab-pygments==0.1.2
jupyterlab-widgets==1.0.0
keyring==23.5.0
kiwisolver==1.4.4
launchpadlib==1.10.16
lazr.restfulclient==0.14.4
lazr.uri==1.0.6
lxml==4.9.1
MarkupSafe==2.1.1
matplotlib==3.7.0
matplotlib-inline==0.1.6
mccabe==0.7.0
mistune==0.8.4
more-itertools==8.10.0
mypy-extensions==0.4.3
nbclassic==0.5.2
nbclient==0.5.13
nbconvert==6.5.4
nbformat==5.7.0
nest-asyncio==1.5.6
nodeenv==1.8.0
notebook==6.5.2
notebook_shim==0.2.2
numpy==1.23.5
oauthlib==3.2.0
packaging==23.2
pandas==1.5.3
pandocfilters==1.5.0
parso==0.8.3
pathspec==0.10.3
patsy==0.5.3
pexpect==4.8.0
pickleshare==0.7.5
Pillow==9.4.0
platformdirs==2.5.2
plotly==5.9.0
pluggy==1.0.0
prometheus-client==0.14.1
prompt-toolkit==3.0.36
protobuf==4.24.0
psutil==5.9.0
psycopg2==2.9.3
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==8.0.0
pyarrow-hotfix==0.5
pycparser==2.21
pydantic==1.10.6
pyflakes==3.1.0
Pygments==2.11.2
PyGObject==3.42.1
PyJWT==2.3.0
pyodbc==4.0.32
pyparsing==3.0.9
pyright==1.1.294
pyrsistent==0.18.0
python-apt==2.4.0+ubuntu4
python-dateutil==2.8.2
python-lsp-jsonrpc==1.1.1
python-lsp-server==1.8.0
pytoolconfig==1.2.5
pytz==2022.7
pyzmq==23.2.0
requests==2.28.1
rope==1.7.0
s3transfer==0.6.2
scikit-learn==1.1.1
scipy==1.10.0
seaborn==0.12.2
SecretStorage==3.3.1
Send2Trash==1.8.0
six==1.16.0
sniffio==1.2.0
soupsieve==2.3.2.post1
ssh-import-id==5.11
stack-data==0.2.0
statsmodels==0.13.5
tenacity==8.1.0
terminado==0.17.1
threadpoolctl==2.2.0
tinycss2==1.2.1
tokenize-rt==4.2.1
tomli==2.0.1
tornado==6.1
traitlets==5.7.1
typing_extensions==4.4.0
ujson==5.4.0
unattended-upgrades==0.1
urllib3==1.26.14
virtualenv==20.16.7
wadllib==1.3.6
wcwidth==0.2.5
webencodings==0.5.1
websocket-client==0.58.0
whatthepatch==1.0.2
widgetsnbextension==3.6.1
yapf==0.33.0
zipp==1.0.0 | 🤖:bug,investigate | low | Critical |
2,556,415,156 | flutter | [Semantics] Add support for setting the heading level on iOS and macOS | ### Use case
This is a follow-up of closed #97894.
iOS and macOS platforms support [AccessibilityHeadingLevel](https://developer.apple.com/documentation/swiftui/accessibilityheadinglevel) which is an equivalent of [ARIA: heading role](https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/Roles/heading_role) on web.
iOS support was mentioned by both the OP and in the comment: https://github.com/flutter/flutter/issues/97894#issuecomment-2150050231 but the related PR #41435 added the heading level support for the web only.
Different heading levels can speed up the navigation in case of VoiceOver users. They can quickly navigate between subsequent headings (either any or at the same level only) using the keyboard shortcuts: https://support.apple.com/guide/voiceover/search-commands-cpvokys08/mac
### Proposal
Required changes are analogous to those made in https://github.com/flutter/engine/pull/41435 for web.
Here is how to set the heading level: https://developer.apple.com/documentation/swiftui/view/accessibilityheading(_:)
iOS/macOS also have 6 heading levels (from 1 to 6) like web. The value of `0` can probably be mapped to [unspecified](https://developer.apple.com/documentation/swiftui/accessibilityheadinglevel/unspecified). | c: new feature,platform-ios,a: accessibility,platform-mac,c: proposal,P2,team-accessibility,triaged-accessibility | low | Minor |
2,556,437,909 | pytorch | Add Mcdropout layer | ### 🚀 The feature, motivation and pitch
I am working with MCDropout, and find the current workflow in pytorch suboptimal and misleading. The current way to enable Dropout at evaluation time to perform MCDropout (https://arxiv.org/pdf/1506.02142) is to set all the Dropout Layers to training mode, which is in my opinion misleading, since you are not training at that point.
My implementation would be to set a second flag `mcdropout` that enables to use the Layer with dropout always turned on, so that one does not need to loop over the layers, maintaining a clearer and cleaner code structure.
This is my suggestion:
```
class MCDropout(_DropoutNd):
"""
Implementation of MCDropout to the torch dropout layer.
This adds a mcdropout flag, which turns dropout always on in training and
evaluation mode.
Args:
p : probability of an element to be zeroed. Default: 0.5
mcdropout: if True, will always perform dropout
inplace : if True, will perform dropout in-place
"""
def __init__(
self, p: float = 0.5, mcdropout: bool = True, inplace: bool = False
) -> None:
super().__init__(p, inplace)
self.mcdroput = mcdropout
def forward(self, input: torch.Tensor) -> torch.Tensor:
return torch.nn.functional.dropout(
input, self.p, self.training or self.mcdropout, self.inplace
)
```
The change adds a parameter `mcdropout` to the Dropout layer, and returns as a condition to use dropout or not `self.training or self.mcdropout`, thus avoiding the need to go over all the layers and turn the training mode on. This also enables to set only some layers to MCDropout layers in an easier way.
### Alternatives
Currently to use mcdropout one has to go over all the modules in the model and set them to training mode.
```def enable_dropout(model):
""" Function to enable the dropout layers during test-time """
for m in model.modules():
if m.__class__.__name__.startswith('Dropout'):
m.train()
```
### Additional context
_No response_
cc @albanD @mruberry @jbschlosser @walterddr @mikaylagawarecki | module: nn,triaged | low | Minor |
2,556,487,569 | TypeScript | A new generic type can be used for file path completion(intellisense) | ### 🔍 Search Terms
"path intellisense","path completion","asset path completion"
### ✅ Viability Checklist
- [X] This wouldn't be a breaking change in existing TypeScript/JavaScript code
- [X] This wouldn't change the runtime behavior of existing JavaScript code
- [X] This could be implemented without emitting different JS based on the types of the expressions
- [X] This isn't a runtime feature (e.g. library functionality, non-ECMAScript syntax with JavaScript output, new syntax sugar for JS, etc.)
- [X] This isn't a request to add a new utility type: https://github.com/microsoft/TypeScript/wiki/No-New-Utility-Types
- [X] This feature would agree with the rest of our Design Goals: https://github.com/Microsoft/TypeScript/wiki/TypeScript-Design-Goals
### ⭐ Suggestion
Add a tool generics so that some function parameters can enable file path type hints
some assets in `../assets`
```ts
function getImageUrl(name:T<"../assets">) {
...
return ...
}
getImageUrl("// intellisense
```
### 📃 Motivating Example
Enable custom file path completion through generics
### 💻 Use Cases
1. What do you want to use this for?
When I used [vite static resource introduction](https://vitejs.dev/guide/assets.html#new-url-url-import-meta-url), I used a function to wrap it, but the function parameters could not achieve type hints like `import`.
the function like:
```ts
function getImageUrl(name:string) { // lost file intellisense
return new URL(`./dir/${name}.png`, import.meta.url).href
}
```
2. What shortcomings exist with current approaches?
Only `import` statements support path completion and cannot be customized
3. What workarounds are you using in the meantime?
i make a vscode extension
| Suggestion,Awaiting More Feedback | low | Minor |
2,556,533,310 | PowerToys | Remapped key in client does BOTH actions on the remote | ### Microsoft PowerToys version
0.84.1
### Installation method
Microsoft Store
### Running as admin
Yes
### Area(s) with issue?
Keyboard Manager
### Steps to reproduce
Just got new Win 11 laptop and found out about Power Toys and it's keyboard remapping feature. I've enabled remapping Caps Lock -> Backspace, Scroll Lock -> Caps Lock and connected to the remote running the windows 10. Tried using remapped key but realised that BOTH original and remap are sent to/executed on remote. Most remote settings on both ends are defaults, I can't remember fiddling with them and the relevant client side settings are as follows:
<img width="291" alt="image" src="https://github.com/user-attachments/assets/25dae5de-f2a5-4850-b98c-aaa94e73375d">
Remote host has the same remapping but done in the registry.
### ✔️ Expected Behavior
Only remapped key to be send to the remote, or at the very least the original one.
### ❌ Actual Behavior
BOTH original and remapped keys are sent
### Other Software
Remote desktop connection | Issue-Bug,Needs-Triage | low | Minor |
2,556,630,050 | vscode | [Accessibility with screen reader] NVDA switch automatically the language in the accessible view of the embedded terminal | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes/No
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.1
- OS Version: Windows 11 professional
- NVDA Version : 2024.3 with the OneCore synthesizer
Steps to Reproduce:
1. Open VSCode with NVDA active
2. CTRL+ù to open the embedded terminal
3. Run a command, like for example in my case "quarto render" then enter to run the command
4. ALT+F2 to open the accessible view of the embedded terminal and listen to the compilation errors
5. i.e. My version of VSCode is in French, via the extension "French Language Pack for Visual Studio Code", because I'm a French native speaker, but the output of the terminal is in English, so I need to switch the language used by my screen reader to English to be able to understand what it is saying, otherwise it will read the content in the accessible view with a French accent, making it unintelligible
6. So I then try to change the language to hear the output of the accessible view, because by default NVDA is reading it with a French voice. To do that, I've tried to change the language on the fly, i.e. without going through the configuration profile, but only with the keys on my keyboard.
7. The selected reading voice become English on every other part of VSCode, except on the accessible view.
Hello,
As a new VSCode and blind user, I'm learning to use the Markdown language, and more specifically Quarto Markdown.
I'm running Windows 11 professional, NVDA 2024.3 with the OneCore synthesizer and the “automatic language detection” option, and VSCode 1.93.1.
I use the ALT+F2 shortcut to access the accessible view of the built-in terminal. Being French, I use VSCode in French thanks to the extension [French Language Pack for Visual Studio Code](https://marketplace.visualstudio.com/items?itemName=MS-CEINTL.vscode-language-pack-fr). When I open the accessible view of the embedded terminal, the textual content displayed by VSCode is in English, which is normal.
But my problem is: how can I listen to this content with my screen reader using the right language voice? I've tried to change the language on the fly, i.e. without going through the configuration profile, but only with the keys on my keyboard. The selected voice is English everywhere, except in the accessible view. It's as if a language tag set the language of this window to French by default. How can I change this?
I hope I've been as clear as possible in my request, this is the first time I've posted an issue here.
Thank you very much, and have a nice day.
Michaël Beuve | bug,accessibility | low | Critical |
2,556,695,014 | vscode | Terminal seems to flicker more than ever | I feel that the terminal flickers more when I resize it, not sure it ever did flicker so much actually:
Did something change in the past weeks?
My terminal related settings:
```json
"terminal.integrated.fontFamily": "Menlo",
"terminal.integrated.fontSize": 13,
"terminal.integrated.lineHeight": 1.4,
"terminal.integrated.windowsEnableConpty": false,
"terminal.integrated.showExitAlert": false,
"terminal.integrated.tabs.enabled": true,
"terminal.integrated.shellIntegration.enabled": true,
"terminal.integrated.stickyScroll.enabled": false,
"terminal.integrated.commandsToSkipShell": [
"workbench.action.openPreviousEditorFromHistory",
"workbench.action.startTerminalSpeechToText",
"workbench.action.stopTerminalSpeechToText"
],
"terminal.integrated.initialHint": false,
``` | bug,terminal-rendering | low | Minor |
2,556,713,513 | electron | [Bug]: Unicode console output on Windows is still problematic | ### Preflight Checklist
- [X] I have read the [Contributing Guidelines](https://github.com/electron/electron/blob/main/CONTRIBUTING.md) for this project.
- [X] I agree to follow the [Code of Conduct](https://github.com/electron/electron/blob/main/CODE_OF_CONDUCT.md) that this project adheres to.
- [X] I have searched the [issue tracker](https://www.github.com/electron/electron/issues) for a bug report that matches the one I want to file, without success.
### Electron Version
32.1.2
### What operating system(s) are you using?
Windows
### Operating System Version
Windows 10 Pro 22H2
### What arch are you using?
x64
### Last Known Working Electron version
_No response_
### Expected Behavior
When logging Unicode strings to the console in an Electron application on Windows, the output should correctly display the Unicode characters.
### Actual Behavior
When running an Electron application on Windows, `console.log` statements containing Unicode strings produce gibberish or unreadable characters in the console output.
To reproduce this issue, you could add the following lines to the beginning of your main process script:
```javascript
console.log('Привет');
console.log('你好');
console.log('こんにちは');
console.log('مرحبا');
console.log('Γειά σου');
```
Instead of displaying the correct Unicode characters, the console output appears as follows:
### Testcase Gist URL
_No response_
### Additional Information
This issue is related to the previously closed issue #5761 (https://github.com/electron/electron/issues/5761). Despite the original issue being closed, the problem still persists. The only known workaround is to run `chcp 65001` every time before running an Electron app.
| platform/windows,bug :beetle:,has-repro-gist,32-x-y | low | Critical |
2,556,721,240 | excalidraw | Add support of Ukrainian (or Cyrillic in general) language for Lilita One and Comic Shanns fonts | Please, add Ukrainian language for following fonts:
- Lilita One
- Comic Shanns
<img width="866" alt="image" src="https://github.com/user-attachments/assets/b017e70d-3c35-4565-bfc4-228fc07bf3b7">
<img width="848" alt="image" src="https://github.com/user-attachments/assets/9cc61510-c72c-48b2-b1a3-ccab78869858"> | font | low | Minor |
2,556,753,754 | pytorch | BCE loss mps device | ### 🐛 Describe the bug
I have a problem training a model with the BCE loss using mps device. The model uses a linear layer to predict a the sign of a real value number (two classes). When I train it in cpu everything is fine, but when i pass to mps the prediction degenerates and predicts always the same "class" for all the training points.
### Versions
Collecting environment information...
PyTorch version: 2.3.0.dev20240229
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: macOS 14.6.1 (arm64)
GCC version: Could not collect
Clang version: Could not collect
CMake version: version 3.29.2
Libc version: N/A
Python version: 3.12.4 | packaged by conda-forge | (main, Jun 17 2024, 10:13:44) [Clang 16.0.6 ] (64-bit runtime)
Python platform: macOS-14.6.1-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Apple M3 Max
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] torch==2.3.0.dev20240229
[pip3] torchaudio==2.2.0.dev20240229
[pip3] torchsummary==1.5.1
[pip3] torchvision==0.18.0.dev20240229
[conda] numpy 1.26.4 pypi_0 pypi
[conda] torch 2.3.0.dev20240229 pypi_0 pypi
[conda] torchaudio 2.2.0.dev20240229 pypi_0 pypi
[conda] torchsummary 1.5.1 pypi_0 pypi
[conda] torchvision 0.18.0.dev20240229 pypi_0 pypi
cc @kulinseth @albanD @malfet @DenisVieriu97 @jhavukainen | triaged,module: correctness (silent),module: mps | low | Critical |
2,556,757,282 | neovim | `gq` fails on empty file with `E20: Mark not set` | ### Problem
Formatting with `gq` and `formatprg` fails on empty file (general new buffer) with error `E20: Mark not set`.
### Steps to reproduce
1. nvim --clean foo
2. `:set formatprg=fmt`
3. type `gqG`
4. command fails with `E20: Mark not set`
tested with these `formatprg` values:
- `fmt`
- `jq`
- `prettier --parser json`
> `formatexpr` seems to be fine. tested with `xmlformat#Format()`, `v:lua.vim.lsp.formatexpr()` and `v:lua.require'conform'.formatexpr()`.
> `:%!fmt` is also fine.
### Expected behavior
`gq` command on empty file should not fail
or print more meaningful error message.
### Nvim version (nvim -v)
v0.11.0-dev-862+gdf915f3af
### Vim (not Nvim) behaves the same?
yes, vim 8.2
### Operating system/version
ubuntu 22.04 (aarch64)
### Terminal name/version
blink shell
### $TERM environment variable
xterm-256color
### Installation
build from repo | bug-vim,marks,normal-mode | low | Critical |
2,556,771,318 | vscode | Inconsistent button order between editor and panel | * open an editor (no tabs)
* open chat view in secondary sidebad
* the overflow (...) and close (X) commands are swapped
IMO the editor does this rignt
<img width="1069" alt="Screenshot 2024-09-30 at 15 56 31" src="https://github.com/user-attachments/assets/40817e6b-e6c5-45d8-b146-d09e2c6c8b7d">
| workbench-tabs,under-discussion,layout | low | Minor |
2,556,854,646 | go | proposal: cmd/go: `-json` flag for `go version -m` | ```
$ go version -m -json ~/go/bin/gopls
flag provided but not defined: -json
usage: go version [-m] [-v] [file ...]
Run 'go help version' for details.
```
VS Code Go (TS/JS) uses `go version -m` when inspecting the tools versions.
If `go version -m` can output JSON-encoded `runtime/debug.BuildSetting` format,
it will help simplifying output parsing a lot. | Proposal,NeedsInvestigation,FeatureRequest,GoCommand,Proposal-FinalCommentPeriod | low | Critical |
2,556,863,985 | yt-dlp | [ixigua] Failed to parse JSON (caused by JSONDecodeError) | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm reporting that yt-dlp is broken on a **supported** site
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/yt-dlp/yt-dlp/wiki/FAQ#video-url-contains-an-ampersand--and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [X] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and I'm willing to share it if required
### Region
china
### Provide a description that is worded well enough to be understood
Error while try to download from ixigua.com.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [ ] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
[debug] Command-line config: ['-vU', 'https://www.ixigua.com/7401795461469700634', '--ignore-config', '--ignore-errors', '--cookies', 'e:\\cookies.txt', '--referer', 'https://www.ixigua.com/']
[debug] Encodings: locale cp936, fs utf-8, pref cp936, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds [6328e2e67] (win_exe)
[debug] Python 3.8.10 (CPython AMD64 64bit) - Windows-10-10.0.19045-SP0 (OpenSSL 1.1.1k 25 Mar 2021)
[debug] exe versions: ffmpeg n7.0.2-19-g45ecf80f0e-20240928 (setts), ffprobe 2.7
[debug] Optional libraries: Cryptodome-3.20.0, brotli-1.1.0, certifi-2024.08.30, curl_cffi-0.5.10, mutagen-1.47.0, requests-2.32.3, sqlite3-3.35.5, urllib3-2.2.3, websockets-13.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets, curl_cffi
[debug] Loaded 1838 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp-nightly-builds/releases/latest
Latest version: nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds
yt-dlp is up to date (nightly@2024.09.29.232819 from yt-dlp/yt-dlp-nightly-builds)
[Ixigua] Extracting URL: https://www.ixigua.com/7401795461469700634
[Ixigua] 740179546146970063: Downloading webpage
ERROR: [Ixigua] 740179546146970063: 740179546146970063: Failed to parse JSON (caused by JSONDecodeError('Extra data in \'atedData" = "functio\': line 2 column 37 (char 37)')); please report this issue on https://github.com/yt-dlp/yt-dlp/issues?q= , filling out the appropriate issue template. Confirm you are on the latest version using yt-dlp -U
File "yt_dlp\extractor\common.py", line 741, in extract
File "yt_dlp\extractor\ixigua.py", line 67, in _real_extract
File "yt_dlp\extractor\ixigua.py", line 42, in _get_json_data
File "yt_dlp\extractor\common.py", line 1093, in _parse_json
File "yt_dlp\extractor\common.py", line 1076, in __print_error
File "yt_dlp\utils\_utils.py", line 552, in decode
File "json\decoder.py", line 340, in decode
json.decoder.JSONDecodeError: Extra data: line 2 column 37 (char 37)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "yt_dlp\extractor\common.py", line 1090, in _parse_json
File "json\__init__.py", line 370, in loads
File "yt_dlp\utils\_utils.py", line 560, in decode
json.decoder.JSONDecodeError: Extra data in 'atedData" = "functio': line 2 column 37 (char 37)
```
| geo-blocked,site-bug,patch-available,needs-testing | low | Critical |
2,556,932,774 | vscode | how to disable Word Wrap globally | ## Environment data
Version: 1.93.1 (system setup)
Commit: 38c31bc77e0dd6ae88a4e9cc93428cc27a56ba40
Date: 2024-09-11T17:20:05.685Z
Electron: 30.4.0
ElectronBuildId: 10073054
Chromium: 124.0.6367.243
Node.js: 20.15.1
V8: 12.4.254.20-electron.0
OS: Windows_NT x64 10.0.22631
## Expected behaviour
Whenver we use the shortcut key "alt + z" it should disable wordwrap on all jupyter Notebook Cells
## Actual behaviour
It is currently running on individual cell level and whenever we reopen the VSCode, it will be wordwrap again, so need to click each cell and click alt + z to remove word wraps
## Steps to reproduce:
1. create multiple notebook input cells with large string data in single line
2. inbetween create input cells with smaller strings
3. and then keep individual input cell unwrapped using alt + z
4. restart the VScode, and you will see all the cell input values are wordwrapped again.
5. even if we save all input cells with unwrapped data ( alt + z ), after vscode restart, it will wrapped again.
Default I have made wordwrap Off everywhere.
In below screenshot it shows "Modified elsewhere" popup, there also I have checked and made settings to Off.
but still issue persists after restarting the VSCode.
| bug | low | Major |
2,556,938,701 | flutter | Create a migrator for android 35/16kb page size cmake flags for plugin_ffi | Follow on work from https://github.com/flutter/flutter/pull/155508 which updates the templates.
Examples of updating the app cmake file here.
Impl file: lib/src/migrations/cmake_native_assets_migration.dart
Test dir: test/general.shard/migrations/cmake_project_migration_test.dart
This bug will need a migrator for the plugin cmake file. | c: new feature,framework,fyi-ecosystem | low | Critical |
2,556,961,325 | ollama | Uneven split across GPUs | When loading a model across 2 GPUs, the layers are split evenly, but the GPU memory usage is quite a bit higher on the first GPU:
```
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3090 On | 00000000:01:00.0 Off | N/A |
| 55% 58C P0 188W / 275W | 23747MiB / 24576MiB | 27% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA GeForce RTX 3090 On | 00000000:02:00.0 Off | N/A |
| 53% 49C P0 179W / 275W | 22519MiB / 24576MiB | 26% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
```
This seems to be due do `CUDA0 compute buffer size` being ~1GB higher than the CUDA1 equivalent. When using text-generation-webui & llamacpp I'm able to specify a `50,51` split which results in the second GPU getting a layer or two more, thus balancing the memory usage, and allowing bigger models to run (or more layers to get offloaded). Does this exist? If not, is it possible?
<details>
<summary>Server log</summary>
```
Sep 30 15:00:25 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:25.780Z level=INFO source=memory.go:326 msg="offload to cuda" layers.requested=78 layers.model=81 layers.offload=70 layers.split=35,35 memory.available="[23.3 GiB 23.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="52.4 GiB" memory.required.partial="45.9 GiB" memory.required.kv="5.0 GiB" memory.required.allocations="[23.0 GiB 22.9 GiB]" memory.weights.total="44.3 GiB" memory.weights.repeating="43.3 GiB" memory.weights.nonrepeating="974.6 MiB" memory.graph.full="2.6 GiB" memory.graph.partial="2.6 GiB"
Sep 30 15:00:25 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:25.783Z level=INFO source=server.go:388 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-c9ff230988a3c90f5beec5da2ebbd8b77d953389b587cb7398c6abd671b7562f --ctx-size 16384 --batch-size 512 --embedding --log-disable --n-gpu-layers 78 --flash-attn --parallel 1 --tensor-split 35,35 --port 37883"
Sep 30 15:00:25 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:25.783Z level=INFO source=sched.go:449 msg="loaded runners" count=1
Sep 30 15:00:25 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:25.783Z level=INFO source=server.go:587 msg="waiting for llama runner to start responding"
Sep 30 15:00:25 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:25.783Z level=INFO source=server.go:621 msg="waiting for server to become available" status="llm server error"
Sep 30 15:00:25 dying-love 6f929011afab[1234]: INFO [main] build info | build=10 commit="3f6ec33" tid="139699938238464" timestamp=1727708425
Sep 30 15:00:25 dying-love 6f929011afab[1234]: INFO [main] system info | n_threads=16 n_threads_batch=16 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="139699938238464" timestamp=1727708425 total_threads=32
Sep 30 15:00:25 dying-love 6f929011afab[1234]: INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="31" port="37883" tid="139699938238464" timestamp=1727708425
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: loaded meta data with 35 key-value pairs and 963 tensors from /root/.ollama/models/blobs/sha256-c9ff230988a3c90f5beec5da2ebbd8b77d953389b587cb7398c6abd671b7562f (version GGUF V3 (latest))
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 0: general.architecture str = qwen2
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 1: general.type str = model
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 2: general.name str = Qwen2.5 72B Instruct
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 3: general.finetune str = Instruct
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 4: general.basename str = Qwen2.5
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 5: general.size_label str = 72B
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 6: general.license str = other
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 7: general.license.name str = qwen
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-7...
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 9: general.base_model.count u32 = 1
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 10: general.base_model.0.name str = Qwen2.5 72B
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 11: general.base_model.0.organization str = Qwen
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-72B
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 13: general.tags arr[str,2] = ["chat", "text-generation"]
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 14: general.languages arr[str,1] = ["en"]
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 15: qwen2.block_count u32 = 80
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 16: qwen2.context_length u32 = 32768
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 17: qwen2.embedding_length u32 = 8192
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 18: qwen2.feed_forward_length u32 = 29568
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 19: qwen2.attention.head_count u32 = 64
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 20: qwen2.attention.head_count_kv u32 = 8
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 21: qwen2.rope.freq_base f32 = 1000000.000000
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 22: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 23: general.file_type u32 = 14
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 25: tokenizer.ggml.pre str = qwen2
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ...
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 151645
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 30: tokenizer.ggml.padding_token_id u32 = 151643
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 31: tokenizer.ggml.bos_token_id u32 = 151643
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - kv 34: general.quantization_version u32 = 2
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type f32: 401 tensors
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type q5_0: 70 tensors
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type q5_1: 10 tensors
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type q4_K: 401 tensors
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type q5_K: 80 tensors
Sep 30 15:00:25 dying-love 6f929011afab[1234]: llama_model_loader: - type q6_K: 1 tensors
Sep 30 15:00:26 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:26.034Z level=INFO source=server.go:621 msg="waiting for server to become available" status="llm server loading model"
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_vocab: special tokens cache size = 22
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_vocab: token to piece cache size = 0.9310 MB
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: format = GGUF V3 (latest)
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: arch = qwen2
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: vocab type = BPE
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_vocab = 152064
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_merges = 151387
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: vocab_only = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_ctx_train = 32768
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_embd = 8192
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_layer = 80
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_head = 64
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_head_kv = 8
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_rot = 128
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_swa = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_embd_head_k = 128
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_embd_head_v = 128
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_gqa = 8
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_embd_k_gqa = 1024
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_embd_v_gqa = 1024
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: f_norm_eps = 0.0e+00
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: f_norm_rms_eps = 1.0e-06
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: f_clamp_kqv = 0.0e+00
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: f_logit_scale = 0.0e+00
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_ff = 29568
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_expert = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_expert_used = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: causal attn = 1
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: pooling type = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: rope type = 2
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: rope scaling = linear
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: freq_base_train = 1000000.0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: freq_scale_train = 1
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: n_ctx_orig_yarn = 32768
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: rope_finetuned = unknown
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: ssm_d_conv = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: ssm_d_inner = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: ssm_d_state = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: ssm_dt_rank = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: ssm_dt_b_c_rms = 0
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: model type = 70B
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: model ftype = Q4_K - Small
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: model params = 72.71 B
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: model size = 40.87 GiB (4.83 BPW)
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: general.name = Qwen2.5 72B Instruct
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: BOS token = 151643 '<|endoftext|>'
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: EOS token = 151645 '<|im_end|>'
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: PAD token = 151643 '<|endoftext|>'
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: LF token = 148848 'ÄĬ'
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: EOT token = 151645 '<|im_end|>'
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_print_meta: max token length = 256
Sep 30 15:00:26 dying-love 6f929011afab[1234]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
Sep 30 15:00:26 dying-love 6f929011afab[1234]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Sep 30 15:00:26 dying-love 6f929011afab[1234]: ggml_cuda_init: found 2 CUDA devices:
Sep 30 15:00:26 dying-love 6f929011afab[1234]: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Sep 30 15:00:26 dying-love 6f929011afab[1234]: Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Sep 30 15:00:26 dying-love 6f929011afab[1234]: llm_load_tensors: ggml ctx size = 1.27 MiB
Sep 30 15:00:27 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:27.490Z level=INFO source=server.go:621 msg="waiting for server to become available" s>
Sep 30 15:00:29 dying-love 6f929011afab[1234]: llm_load_tensors: offloading 78 repeating layers to GPU
Sep 30 15:00:29 dying-love 6f929011afab[1234]: llm_load_tensors: offloaded 78/81 layers to GPU
Sep 30 15:00:29 dying-love 6f929011afab[1234]: llm_load_tensors: CPU buffer size = 41850.31 MiB
Sep 30 15:00:29 dying-love 6f929011afab[1234]: llm_load_tensors: CUDA0 buffer size = 19646.28 MiB
Sep 30 15:00:29 dying-love 6f929011afab[1234]: llm_load_tensors: CUDA1 buffer size = 19530.78 MiB
Sep 30 15:00:29 dying-love 6f929011afab[1234]: time=2024-09-30T15:00:29.545Z level=INFO source=server.go:621 msg="waiting for server to become available" s>
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: n_ctx = 16384
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: n_batch = 512
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: n_ubatch = 512
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: flash_attn = 1
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: freq_base = 1000000.0
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: freq_scale = 1
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_kv_cache_init: CUDA_Host KV buffer size = 128.00 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_kv_cache_init: CUDA0 KV buffer size = 2496.00 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_kv_cache_init: CUDA1 KV buffer size = 2496.00 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: KV self size = 5120.00 MiB, K (f16): 2560.00 MiB, V (f16): 2560.00 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: CUDA_Host output buffer size = 0.61 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: CUDA0 compute buffer size = 1287.53 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: CUDA1 compute buffer size = 163.50 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: CUDA_Host compute buffer size = 48.01 MiB
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: graph nodes = 2487
Sep 30 15:00:32 dying-love 6f929011afab[1234]: llama_new_context_with_model: graph splits = 33
```
</details> | bug,memory | low | Critical |
2,556,980,587 | vscode | [json] Add support for extensions associating JSON schemas with documents dynamically (via API) | <!-- ⚠️⚠️ Do Not Delete This! feature_request_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- Please search existing issues to avoid creating duplicates. -->
<!-- Describe the feature you'd like. -->
Add support for extensions associating JSON schemas with documents dynamically (via API).
Right now, it is only possible to associate a JSON schema with a text document by:
1. using schemas directly built-in into VSCode, e.g., `package.json`, `.babelrc` , ...
2. explicitly [mapping it in the user settings](https://code.visualstudio.com/docs/languages/json#_mapping-in-the-user-settings)
3. explicitly [mapping it in the workspace](https://code.visualstudio.com/docs/languages/json#_mapping-to-a-schema-in-the-workspace)
4. explicitly [mapping it in an extension via a file-match pattern](https://code.visualstudio.com/docs/languages/json#_file-match-syntax)
But all these associations are static and working only on a folder path and filename matching.
I would like to be able to dynamically/programmatically associate a JSON schema with a document within an extension.
E.g., the extension could first inspect the content of the file and check for specific well-known conditions in order to decide, which JSON schema (or if at all) should be associated with a given text document.
E.g., within our organization we have a lot of different file formats with existing JSON schemas, but we don't have canonical/standardized folders and filenames for the files that would need validation against these JSON schemas, with most of them just ending on `*.json` somewhere in the folder tree.
I could imagine a mechanism like this to associate a JSON schema with a JSON document `doc`:
```
registerJsonSchema(doc, schemaId, schemaSrc)
```
with a unique `schemaId` provided by the extension and `schemaSrc` either be `URL` or a local file reference.
If the same `schemaId` is provided for a `doc` with no `schemaSrc` the JSON schema association is removed again from that document.
Theoretically `schemaSrc` could also be a JSON schema object (similar to a [schema directly defined in the settings](https://code.visualstudio.com/docs/languages/json#_mapping-to-a-schema-defined-in-settings)), which would allow you to dynamically build up a schema by the extension and provide this for validation.
And since a lot of configuration files are not just `JSON` files but also `YAML` files, some bonus points for allowing the association of JSON schemas also to `YAML` files, not just `JSON` files.
Note, that there is also another related feature request: `Support for contentMatch in addition to fileMatch for extension contributes.jsonValidation` https://github.com/microsoft/vscode/issues/229696 | feature-request,json | low | Minor |
2,556,991,410 | go | runtime:cpu1: TestGdbAutotmpTypes failures | ```
#!watchflakes
default <- pkg == "runtime:cpu1" && test == "TestGdbAutotmpTypes"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8735486120996203153)):
=== RUN TestGdbAutotmpTypes
=== PAUSE TestGdbAutotmpTypes
=== CONT TestGdbAutotmpTypes
runtime-gdb_test.go:78: gdb version 15.0
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation,arch-riscv,compiler/runtime | low | Critical |
2,556,992,186 | TypeScript | undefined is narrowed away incorrectly | ### 🔎 Search Terms
narrowing undefined, incorrect type narrowing, incorrect if statement narrowing
### 🕗 Version & Regression Information
- This changed between versions 5.2 and 5.3
### ⏯ Playground Link
https://www.typescriptlang.org/play/?#code/CYUwxgNghgTiAEkoGdnwILwN4CgCQAksugBQCUAXPAC4AWAlmoxgNw4C+OOoSciA9gDtk1eAAco1aiBiCqmAD7wAroNAAzeoJDA261WGr0h8KGLEQAngAVJ02eWz566+CQlSZggPwA6IqRk8AC8ofDqUBDIIEG4eHge9oJs8QD0qfAAet74eHDUyrIpnAl2XinpWTnsQA
### 💻 Code
```ts
declare class A {
IsA(): this is A;
}
declare const pattern: A | undefined;
function applyPattern() {
if (pattern?.IsA() === false) {
pattern;
// ^?
return;
}
pattern;
// ^?
}
```
### 🙁 Actual behavior
`pattern` is narrowed down to `A`, removing the undefined
### 🙂 Expected behavior
`pattern` should only be narrowed to `A | undefined`
### Additional information about the issue
_No response_ | Bug,Help Wanted | low | Minor |
2,557,016,328 | pytorch | [RFC] Flight Precheck: ahead-of-hang collective mismatch detection | ### 🚀 The feature, motivation and pitch
Wondering if we would be interested in making a UX like this:
```
with flight_precheck:
# user program
```
A couple motivations:
(1) Would allow/encourage users to actively narrow a region for debugging, for example, 1 iteration. So that analysis is simpler.
(2) Would leverage the fact that CPU runs ahead of GPU — when the context is exited, it can do a CPU-based all-gather (or similar) and pre-check, thus analysis made online / ahead of time.
(3) The torch lib would contain the analysis algorithm, mitigating the need for releasing separate software (not easy to maintain if torch lib changes its recording format).
(4) Can mostly reuse today’s FR tracing infra.
Cc: @c-p-i-o
### Alternatives
_No response_
### Additional context
_No response_
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,triaged | low | Critical |
2,557,027,641 | flutter | sample code for `Custom image providers` throwing error on run | ### Page URL
https://api.flutter.dev/flutter/widgets/Image-class.html
### Page source
_No response_
### Describe the problem
<img width="967" alt="image" src="https://github.com/user-attachments/assets/4335f8d8-0895-4805-8c92-013b8029f089">
Error message:
```shell
unsupported library on the web: 'dart:io'
Try removing the import and usage of the library.
Unsupported operation: Platform._version
```
### Expected fix
Need to fix the given sample code to run with out error
### Additional context
_No response_
### I would like to fix this problem.
- [ ] I will try and fix this problem on docs.flutter.dev. | framework,d: api docs,d: examples,platform-web,P2,team-framework,triaged-framework | low | Critical |
2,557,052,974 | pytorch | [RFC] ProcessGroupNCCL uses non-blocking API by default | ### 🚀 The feature, motivation and pitch
## Motivation:
- Gives better fault tolerance against hangs in comm init, comm destroy and P2P operations (involves dynamic connection performed by CPU).
- Allow overlap between NCCL init and other stuff users want the main thread to do (e.g., model or data loader init)
Here "non-blocking" refers to whether a NCCL API call would immediately return or block the host CPU (Traditionally, some NCCL APIs such as ncclCommInitRank may block for a little when rendezvous is performed.)
If the user wants the main thread to do other stuff while NCCL is initializing, this mode would also help as it puts NCCL init to the background.
### Alternatives
_No response_
### Additional context
This knob is control by PyTorch here:
https://github.com/pytorch/pytorch/blob/26956980c6953b42e57ad889b87444c4abccec1c/torch/csrc/distributed/c10d/NCCLUtils.cpp#L90-L97
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,module: nccl,module: c10d | low | Minor |
2,557,072,866 | pytorch | pre-dispatch tracing can't interpose on detach() calls from the autograd engine. | This boils down to the fact that our pre-dispatch mode stack is implemented in pure python, while our "normal" mode stack has C++ TLS associated with it.
Say we want to trace out calls to `.backward()` using a "pre-dispatch" proxy mode.
Autograd sometimes detaches saved variables while it executes the backward. It doesn't call `TensorBase::detach()` though - it calls `tensor.getIntrusivePtr()->shallow_copy_and_detach(...)` ([link](https://github.com/pytorch/pytorch/blob/main/torch/csrc/autograd/variable.h#L897))
`TensorImpl::shallow_copy_and_detach_core` has some special logic to figure out when it should dispatch to python, by consulting the C++ TLS about if there are any modes active ([link](https://github.com/pytorch/pytorch/blob/c13c7e11c553b2a848c158c8e2a5e20bbd5d7f1c/c10/core/TensorImpl.cpp#L499)).
Our pre-dispatch mode stack doesn't have any C++ TLS, though, which means that `shallow_copy_and_detach()` won't know to dispatch to any pre-dispatch modes.
cc @ezyang @chauhang @penguinwu @zou3519 @yf225 | triaged,oncall: pt2,module: ProxyTensor,module: pt2-dispatcher | low | Minor |
2,557,085,292 | pytorch | [RFC] Investigate multi-thread support of c10d | ### 🚀 The feature, motivation and pitch
There are two drivers for this investigation:
- People are starting to use torch.distributed APIs in multi-thread mode. We should investigate which usage is supported and which are not. For the mode not supported, we should document it so that it won't become a support of fait accompli.
- Python 3.13t is coming (Oct 2024). This is the first official version with option to disable GIL. There may be interest in inference, data loading, etc, where torch.distributed should be compatible.
### Alternatives
_No response_
### Additional context
_No response_
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,module: c10d | low | Minor |
2,557,120,862 | pytorch | [RFC] Use NCCL topology detection for Inductor communication time estimation | ### 🚀 The feature, motivation and pitch
Today the bandwidth numbers in Inductor are more or less fixed, regardless of the system the job runs on.
NCCL topology detection identifies whether the system is on NVLink, PCI-e, IB, or TCP sockets, and can provide a bandwidth matrix. A bonus is that the numbers have been sync'ed across all ranks, so that we can avoid different decisions made by compilers on different ranks.
See https://github.com/NVIDIA/nccl/issues/830 for an example of the matrix.
### Alternatives
_No response_
### Additional context
_No response_
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o @ezyang @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @xuanzhang816 | oncall: distributed,triaged,module: nccl,oncall: pt2,module: inductor | low | Minor |
2,557,134,462 | ollama | ollama does not detect Quadro RTX 4000 - cuda driver library failed to get device context 801 | ### What is the issue?
Hi All,
I installed ollama both (on machine/docker) both with same behaviour of not detecting the GPU. Have LM Studio on the same machine which picks up GPU without any issues.
```
root@d50a3f8d8474:/# ollama run phi3.5:3.8b-mini-instruct-q2_K ""
root@d50a3f8d8474:/# ollama ps
NAME ID SIZE PROCESSOR UNTIL
phi3.5:3.8b-mini-instruct-q2_K 45b8dc82a846 5.3 GB 100% CPU 4 minutes from now
```
**Installation**
```
[root@ai ~]# curl -fsSL https://ollama.com/install.sh | sh
>>> Installing ollama to /usr/local
>>> Downloading Linux amd64 bundle
######################################################################## 100.0%#=#=# ######################################################################## 100.0%
>>> Creating ollama user...
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
>>> NVIDIA GPU installed.
```
*Logs from package installation*
```
[root@ai ~]# OLLAMA_DEBUG=1 ollama serve
Error: listen tcp 127.0.0.1:11434: bind: address already in use
[root@ai ~]# systemctl stop ollama
[root@ai ~]# OLLAMA_DEBUG=1 ollama serve
2024/09/29 03:47:20 routes.go:1153: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2024-09-29T03:47:20.643-05:00 level=INFO source=images.go:753 msg="total blobs: 10"
time=2024-09-29T03:47:20.672-05:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-09-29T03:47:20.672-05:00 level=INFO source=routes.go:1200 msg="Listening on 127.0.0.1:11434 (version 0.3.12)"
time=2024-09-29T03:47:20.673-05:00 level=INFO source=common.go:135 msg="extracting embedded files" dir=/tmp/ollama3184037398/runners
time=2024-09-29T03:47:20.673-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu payload=linux/amd64/cpu/libggml.so.gz
time=2024-09-29T03:47:20.673-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu payload=linux/amd64/cpu/libllama.so.gz
time=2024-09-29T03:47:20.673-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu payload=linux/amd64/cpu/ollama_llama_server.gz
time=2024-09-29T03:47:20.673-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx payload=linux/amd64/cpu_avx/libggml.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx payload=linux/amd64/cpu_avx/libllama.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx payload=linux/amd64/cpu_avx/ollama_llama_server.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx2 payload=linux/amd64/cpu_avx2/libggml.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx2 payload=linux/amd64/cpu_avx2/libllama.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cpu_avx2 payload=linux/amd64/cpu_avx2/ollama_llama_server.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v11 payload=linux/amd64/cuda_v11/libggml.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v11 payload=linux/amd64/cuda_v11/libllama.so.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v11 payload=linux/amd64/cuda_v11/ollama_llama_server.gz
time=2024-09-29T03:47:20.674-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v12 payload=linux/amd64/cuda_v12/libggml.so.gz
time=2024-09-29T03:47:20.675-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v12 payload=linux/amd64/cuda_v12/libllama.so.gz
time=2024-09-29T03:47:20.675-05:00 level=DEBUG source=common.go:168 msg=extracting runner=cuda_v12 payload=linux/amd64/cuda_v12/ollama_llama_server.gz
time=2024-09-29T03:47:20.675-05:00 level=DEBUG source=common.go:168 msg=extracting runner=rocm_v60102 payload=linux/amd64/rocm_v60102/libggml.so.gz
time=2024-09-29T03:47:20.675-05:00 level=DEBUG source=common.go:168 msg=extracting runner=rocm_v60102 payload=linux/amd64/rocm_v60102/libllama.so.gz
time=2024-09-29T03:47:20.676-05:00 level=DEBUG source=common.go:168 msg=extracting runner=rocm_v60102 payload=linux/amd64/rocm_v60102/ollama_llama_server.gz
time=2024-09-29T03:47:32.712-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/cpu/ollama_llama_server
time=2024-09-29T03:47:32.712-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/cpu_avx/ollama_llama_server
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/cpu_avx2/ollama_llama_server
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/cuda_v11/ollama_llama_server
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/cuda_v12/ollama_llama_server
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=common.go:294 msg="availableServers : found" file=/tmp/ollama3184037398/runners/rocm_v60102/ollama_llama_server
time=2024-09-29T03:47:32.713-05:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[rocm_v60102 cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]"
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=common.go:50 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY"
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-09-29T03:47:32.713-05:00 level=INFO source=gpu.go:199 msg="looking for compatible GPUs"
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=gpu.go:86 msg="searching for GPU discovery libraries for NVIDIA"
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=gpu.go:468 msg="Searching for GPU library" name=libcuda.so*
time=2024-09-29T03:47:32.713-05:00 level=DEBUG source=gpu.go:491 msg="gpu library search" globs="[/usr/local/lib/ollama/libcuda.so* /usr/local/cuda/lib64/libcuda.so* /root/libcuda.so* /usr/local/cuda*/targets/*/lib/libcuda.so* /usr/lib/*-linux-gnu/nvidia/current/libcuda.so* /usr/lib/*-linux-gnu/libcuda.so* /usr/lib/wsl/lib/libcuda.so* /usr/lib/wsl/drivers/*/libcuda.so* /opt/cuda/lib*/libcuda.so* /usr/local/cuda/lib*/libcuda.so* /usr/lib*/libcuda.so* /usr/local/lib*/libcuda.so*]"
time=2024-09-29T03:47:32.715-05:00 level=DEBUG source=gpu.go:525 msg="discovered GPU libraries" paths=[/usr/lib64/libcuda.so.560.35.03]
CUDA driver version: 12.6
time=2024-09-29T03:47:32.878-05:00 level=DEBUG source=gpu.go:118 msg="detected GPUs" count=1 library=/usr/lib64/libcuda.so.560.35.03
time=2024-09-29T03:47:32.907-05:00 level=INFO source=gpu.go:252 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801"
time=2024-09-29T03:47:32.907-05:00 level=DEBUG source=amd_linux.go:376 msg="amdgpu driver not detected /sys/module/amdgpu"
time=2024-09-29T03:47:32.907-05:00 level=INFO source=gpu.go:347 msg="no compatible GPUs were discovered"
releasing cuda driver library
time=2024-09-29T03:47:32.907-05:00 level=INFO source=types.go:107 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="251.1 GiB" available="240.5 GiB"
```
**Logs from Docker installation**
```
[root@ai ~]# docker logs -f ollama
2024/09/30 15:58:28 routes.go:1153: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2024-09-30T15:58:28.508Z level=INFO source=images.go:753 msg="total blobs: 6"
time=2024-09-30T15:58:28.509Z level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-09-30T15:58:28.509Z level=INFO source=routes.go:1200 msg="Listening on [::]:11434 (version 0.3.12)"
time=2024-09-30T15:58:28.510Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx cpu_avx2 cuda_v11 cuda_v12 cpu]"
time=2024-09-30T15:58:28.510Z level=INFO source=gpu.go:199 msg="looking for compatible GPUs"
time=2024-09-30T15:58:28.670Z level=INFO source=gpu.go:252 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801"
time=2024-09-30T15:58:28.670Z level=INFO source=gpu.go:347 msg="no compatible GPUs were discovered"
time=2024-09-30T15:58:28.670Z level=INFO source=types.go:107 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="251.1 GiB" available="240.4 GiB"
[GIN] 2024/09/30 - 15:59:07 | 200 | 94.19µs | 127.0.0.1 | HEAD "/"
[GIN] 2024/09/30 - 15:59:07 | 200 | 10.954794ms | 127.0.0.1 | POST "/api/show"
time=2024-09-30T15:59:07.334Z level=INFO source=server.go:103 msg="system memory" total="251.1 GiB" free="240.5 GiB" free_swap="4.0 GiB"
time=2024-09-30T15:59:07.334Z level=INFO source=memory.go:326 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[240.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="8.3 GiB" memory.required.partial="0 B" memory.required.kv="4.0 GiB" memory.required.allocations="[8.3 GiB]" memory.weights.total="7.4 GiB" memory.weights.repeating="7.3 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="681.0 MiB"
time=2024-09-30T15:59:07.338Z level=INFO source=server.go:388 msg="starting llama server" cmd="/usr/lib/ollama/runners/cpu_avx2/ollama_llama_server --model /root/.ollama/models/blobs/sha256-8934d96d3f08982e95922b2b7a2c626a1fe873d7c3b06e8e56d7bc0a1fef9246 --ctx-size 8192 --batch-size 512 --embedding --log-disable --no-mmap --numa distribute --parallel 4 --port 39753"
time=2024-09-30T15:59:07.339Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-09-30T15:59:07.339Z level=INFO source=server.go:587 msg="waiting for llama runner to start responding"
time=2024-09-30T15:59:07.339Z level=INFO source=server.go:621 msg="waiting for server to become available" status="llm server error"
WARNING: /proc/sys/kernel/numa_balancing is enabled, this has been observed to impair performance
INFO [main] build info | build=10 commit="070c75f" tid="140389372093376" timestamp=1727711947
INFO [main] system info | n_threads=20 n_threads_batch=20 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="140389372093376" timestamp=1727711947 total_threads=40
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="39" port="39753" tid="140389372093376" timestamp=1727711947
llama_model_loader: loaded meta data with 23 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-8934d96d3f08982e95922b2b7a2c626a1fe873d7c3b06e8e56d7bc0a1fef9246 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
```
I am able to get all the outputs
```
[root@ai ~]# nvidia-smi
Sat Sep 28 01:07:12 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 Quadro RTX 4000 Off | 00000000:37:00.0 Off | N/A |
| 30% 34C P8 9W / 125W | 1MiB / 8192MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+
```
```
[root@ai ~]# nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Wed_Aug_14_10:10:22_PDT_2024
Cuda compilation tools, release 12.6, V12.6.68
Build cuda_12.6.r12.6/compiler.34714021_0
```
**OS**
Linux Rocky 9.4
```
[root@ai ~]# uname -r
5.14.0-427.37.1.el9_4.x86_64
```
**logs**
```
[root@ai ~]# sudo dmesg | grep -i nvidia
[ 1.704573] Loaded X.509 cert 'Rocky Enterprise Software Foundation: Nvidia GPU OOT Signing 101: 816ba9c770e6960cefe378020865d4ebbc352a7d'
[ 6.270595] input: HDA NVidia HDMI/DP,pcm=3 as /devices/pci0000:36/0000:36:00.0/0000:37:00.1/sound/card0/input6
[ 6.270694] input: HDA NVidia HDMI/DP,pcm=7 as /devices/pci0000:36/0000:36:00.0/0000:37:00.1/sound/card0/input7
[ 6.270796] input: HDA NVidia HDMI/DP,pcm=8 as /devices/pci0000:36/0000:36:00.0/0000:37:00.1/sound/card0/input8
[ 6.270843] input: HDA NVidia HDMI/DP,pcm=9 as /devices/pci0000:36/0000:36:00.0/0000:37:00.1/sound/card0/input9
[ 7.812685] nvidia: loading out-of-tree module taints kernel.
[ 7.812696] nvidia: module license 'NVIDIA' taints kernel.
[ 7.836076] nvidia: module verification failed: signature and/or required key missing - tainting kernel
[ 7.950180] nvidia-nvlink: Nvlink Core is being initialized, major device number 510
[ 7.951760] nvidia 0000:37:00.0: enabling device (0140 -> 0143)
[ 7.951842] nvidia 0000:37:00.0: vgaarb: VGA decodes changed: olddecodes=io+mem,decodes=none:owns=none
[ 8.001592] NVRM: loading NVIDIA UNIX x86_64 Kernel Module 560.35.03 Fri Aug 16 21:39:15 UTC 2024
[ 8.115320] nvidia_uvm: module uses symbols from proprietary module nvidia, inheriting taint.
[ 8.252789] nvidia-uvm: Loaded the UVM driver, major device number 508.
[ 8.307886] nvidia-modeset: Loading NVIDIA Kernel Mode Setting Driver for UNIX platforms 560.35.03 Fri Aug 16 21:21:48 UTC 2024
[ 8.323807] [drm] [nvidia-drm] [GPU ID 0x00003700] Loading driver
[ 9.814993] [drm] Initialized nvidia-drm 0.0.0 20160202 for 0000:37:00.0 on minor 1
[ 9.815921] nvidia 0000:37:00.0: [drm] Cannot find any crtc or sizes
```
**additional logs**
```
[root@ai ~]# sudo dmesg | grep -i nvrm
[ 8.001592] NVRM: loading NVIDIA UNIX x86_64 Kernel Module 560.35.03 Fri Aug 16 21:39:15 UTC 2024
```
### OS
Linux
### GPU
Nvidia
### CPU
Intel
### Ollama version
0.3.12 | bug,linux,nvidia,needs more info | low | Critical |
2,557,152,512 | PowerToys | *Multiply NumPad missing as an option to rekey from or to | ### Microsoft PowerToys version
v0.84.1
### Installation method
Microsoft Store
### Running as admin
No
### Area(s) with issue?
Keyboard Manager
### Steps to reproduce
Remapping -subtract key to *multiply key and *multiply key to -subtract key on NumPad
### ✔️ Expected Behavior
I expect to be able to choose the * (multiply) key from the drop down under Select. It does not exist in the drop downs for either Select or To Send.
### ❌ Actual Behavior
When selecting - (subtract) in the Select column, I can switch to Send Text in the To Send section and enter an * Asterisk.
The * (multiply) NumPad key then needs to be remapped, but I can't remap it because the option doesn't appear in the dropdown.
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,557,187,369 | godot | SkeletonModification2DCCDIK causes errors when a second instance of itself it instantiated | ### Tested versions
Godot version
v4.3.stable.official [77dcf97d8]
System information
Windows 10, ryzen 5, radeon 3080
### System information
v4.3.stable.official [77dcf97d8], Windows 10, ryzen 5, radeon 3080
### Issue description
When using SkeletonModification2DCCDIK within SkeletonModificationStack2D editor displays huge amount of error messages (before execution).
However this happens only when SkeletonModification2DCCDIK is present (not deleted) **AND** a second instance of the character is loaded.
A single instance of the character works perfectly fine.
### Steps to reproduce
-Create Skeleton2D (based on Poylgon2D)
-Assign SkeletonModificationStack2D and SkeletonModification2DCCDIK
-Load Character scene into a new project
-Duplicate character scene
### Minimal reproduction project (MRP)
[minimal test.zip](https://github.com/user-attachments/files/17193664/minimal.test.zip)
| bug,topic:animation | low | Critical |
2,557,193,410 | pytorch | [RFC] Allow user to abort group (followed by custom recovery) | ### 🚀 The feature, motivation and pitch
Advanced users want to control ProcessGroup abort and recovery, instead of being controlled by watchdog (such as SIGABRT). See https://github.com/pytorch/pytorch/issues/136312 for such ask.
In this situation, an abort group API is necessary because that's the only way to stop a spinning NCCL kernel.
There is a draft `_abort_process_group` implementation in https://github.com/pytorch/pytorch/pull/132291.
Next step is to formalize it, test it and expose as user API.
### Alternatives
_No response_
### Additional context
_No response_
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,module: c10d | low | Minor |
2,557,223,454 | pytorch | [RFC] Accelerate intra-node communication via NCCL buffer registration | ### 🚀 The feature, motivation and pitch
Registering user buffer with NCCL allows for zero copy.
While `ncclCommRegister` API allowed this for network operations previously, NCCL 2.23 also allows this for intra-node operations.
This is an investigation task wrt:
- how to integrate this feature in ProcessGroupNCCL;
- how to expose this capability to user;
- how to integrate into Inductor memory planning.
Related to Symmetric Memory, async TP. Cc: @yifuwang
### Alternatives
_No response_
### Additional context
_No response_
cc @XilunWu @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,module: nccl | low | Minor |
2,557,261,310 | TypeScript | [Control flow] Array filter with typeguard works differently following array initial value | ### 🔎 Search Terms
filter + typeguard + control flow + strictNullChecks
### 🕗 Version & Regression Information
- This is the behavior in every version I tried, and I reviewed the FAQ for entries about filter + typeguards + control flow + strictNullChecks
### ⏯ Playground Link
https://www.typescriptlang.org/play/?strict=false&noImplicitAny=false&strictFunctionTypes=false&strictPropertyInitialization=false&strictBindCallApply=false&noImplicitThis=false&noImplicitReturns=false&alwaysStrict=false&esModuleInterop=false&declaration=false&target=0&jsx=0&module=0&ts=5.6.2&experimentalDecorators=false&emitDecoratorMetadata=false#code/MYewdgzgLgBATgQwO4C4bTgSzAcwNoC6MAPjAIJyICeAPBtjiTGAK4A2bAfDALwyEBuAFBDQkWADNMbKAFM4sgCZp6uQr3jIAdFJnyAFPuiyADiqhZcTVhwCU50zEwR0Fhr25QqJ2SAmvHHiCYAHJVHBDbGAB6aJgAaQB5ETFoV0scACVkcwz1UgpqOjcrUhsuDTwAIhM2EBMqgmFRcDTwgDFpOQVldIZ1PnDspB0ugyM5Mz7S5nY2ewCTJxdwjxgvHz9F3mCwkoio2ITklvFZjmHc-qICygRaVbK57j48cqaU1thyzr0eq7URD45WGoz+hmMU0e53mDiWzmmjB4nm8vn8kJ2fD2GUiMTiiXinzO5QACmwWBAAMr7S6I-LkO4PfbWZ6VGp1BoAGhhH1OaVJ5Kp+1+3SUAPwQJhZIp1IyoN03Qhk3FLLscOWiLWGzR2yCWPCuKOBKEQA
### 💻 Code
```ts
const raw: string[] | (string | null)[] = [];
const filtered: string[] = raw.filter((step: string | null): step is string => typeof step === 'string') // KO
// Type '(string | null)[]' is not assignable to type 'string[]'.
```
```ts
const raw: string[] |(string | null)[] = ["plop", null];
const filtered: string[] = raw.filter((step: string | null): step is string => typeof step === 'string') // OK no error
```
### 🙁 Actual behavior
There is a strange difference in control flow when you filter nullish values in an array regarding the declaration of that array. This is definitely a edge case. The type `string[] | (string | null)[]` comes from an union type in my case.
### 🙂 Expected behavior
No difference and typeguard should work (regardless the fact it is valid).
### Additional information about the issue
I first thought it was a regression due to #57465 but I tested it on several version. The issue has always been here. I looked into a lot of issues about typeguards and filters but unfortunately, could not find one similar to my issue :cry:
Thanks anyway for the great job | Help Wanted,Possible Improvement | low | Critical |
2,557,286,643 | godot | (Funny) Godot icon looking extended in Task Manager | ### Tested versions
- Reproducible in: `master`
### System information
Windows 11 24H2 and 23H2 - `master`
### Issue description
### Steps to reproduce
- Launch Godot
- Launch Task Manager
### Minimal reproduction project (MRP)
N/A | bug,platform:windows,topic:porting,topic:thirdparty | low | Minor |
2,557,293,752 | flutter | DD for missing Semantics role | ### Document Link
https://flutter.dev/go/semantics-roles
### What problem are you solving?
Audit the missing semantics roles in flutter | a: accessibility,P3,design doc,:scroll:,team-accessibility,triaged-accessibility | low | Minor |
2,557,303,538 | go | proposal: syscall/js: method or function to await a js.Value | ### Proposal Details
Let's say I have an async JavaScript function:
```js
globalThis.myAsyncFunction = async () => 42;
```
Ideally I would be able to do one of these:
```go
var n int
n = js.Global().Call("myAsyncFunction").Wait().Int()
n = js.Global().Call("myAsyncFunction").Await().Int()
n = js.Await(js.Global().Call("myAsyncFunction")).Int()
n = (<-js.Global().Call("myAsyncFunction").Chan()).Int()
```
Creating a promise in Go code for use by JavaScript code is _ok_-ish (it's not great): just use the `new Promise(callback)` constructor with a Go-defined `js.Func` callback.
```go
var jsDoThingCallback = js.FuncOf(func(this Value, args []Value) interface{} {
r1 := <-myChannelFromSomewhere
r2, err := someFuncThatUsesChans(r1)
if err != nil {
args[1].Invoke(errorConstructor.New(err.Error()))
return nil
}
r3, err := someFuncThatSleeps(r2)
if err != nil {
args[1].Invoke(errorConstructor.New(err.Error()))
return nil
}
args[0].Invoke(r3)
return nil
})
func DoThingAsync() js.Value {
return promiseConstructor.New(jsDoThingCallback)
}
```
The other direction -- unwrapping a JavaScript `Promise` instance on the Go-side by waiting for it -- is worse.
```go
// Ugh. I have to manage this intermediate channel myself and remember to handle some edge cases.
var n int
p := promiseConstructor.Call("resolve", js.Global().Call("myAsyncFunction"))
type result struct {
value js.Value
err error
}
ch := make(chan result, 1)
onFulfilled := js.FuncOf(func(this js.Value, args []js.Value) interface{} {
ch <- result{args[0], nil}
close(ch)
return nil
})
defer onFulfilled.Release()
onRejected := js.FuncOf(func(this js.Value, args []js.Value) interface{} {
ch <- result{js.Value{}, js.Error{args[0]}}
close(ch)
return nil
})
defer onRejected.Release()
p.Call("then", onFulfilled, onRejected)
r := <-ch
if r.err != nil {
panic(r.err)
}
n = r.value.Int()
// Would have to do *all that again* for another `await nextFunctionThatUsesResult(n)` 😭
```
Here's the algorithm for the ECMAScript 2025 `Await( value )` abstract operation: https://tc39.es/ecma262/multipage/control-abstraction-objects.html#await
It seems like the `.Wait()` method convention is already in the standard library with `sync.WaitGroup` `wg.Wait()`. Here's an idea for how that might look in Go code. I'm not a Go channels wizard so this might be the completely wrong way to do this.
```go
// Wait waits for the thenable v to fulfill or reject and returns the resulting value or error.
// This is equivalent to the await operator in JavaScript.
func (v js.Value) Wait() (js.Value, error) {
p := promiseConstructor.Call("resolve", v)
type result struct {
value js.Value
err error
}
ch := make(chan result, 1)
onFulfilled := js.FuncOf(func(this js.Value, args []js.Value) interface{} {
ch <- result{args[0], nil}
close(ch)
return nil
})
defer onFulfilled.Release()
onRejected := js.FuncOf(func(this js.Value, args []js.Value) interface{} {
ch <- result{js.Value{}, js.Error{args[0]}}
close(ch)
return nil
})
defer onRejected.Release()
p.Call("then", onFulfilled, onRejected)
r := <-ch
// Unsure if want to panic on error, or return the error.
// If a synchronous function throws an error it panics. Don't know whether to stick
// to that convention or to return a (js.Value, error) multivalue.
return r.value, r.err
// OR
if r.err == nil {
return r.value
} else {
panic(r.err)
}
}
```
There's already some of this promise stuff in the Go standard library https://github.com/golang/go/blob/1d0f5c478ac176fa99d0f3d6bd540e5fb422187a/src/net/http/roundtrip_js.go#L129-L245 so it seems like this is a _thing that people need to do_. I think that providing a `.Wait()` or `Await(v)` or something would be a good way to "one good way to do it"-ify this. | Proposal | low | Critical |
2,557,366,732 | godot | Global illumination doesn't update when force drawing a `SubViewport` if main viewport is disabled | ### Tested versions
- 4.4.dev
- 4.3.1.rc
### System information
Godot v4.4.dev (e3213aaef) - Windows 11 - Vulkan (Forward+) - dedicated NVIDIA GeForce RTX 3070 (NVIDIA; 31.0.15.4633)
### Issue description
SDFGI takes some frames to converge the global illumination (setting `rendering/global_illumination/sdfgi/frames_to_converge`).
However, when force drawing a `SubViewport` like the below example, global illumination doesn't update if the main viewport is disabled.
```gdscript
func _render_subviewport(subviewport: SubViewport, iterations: int = 30, disable_main = true) -> Image:
var scene_tree = Engine.get_main_loop() as SceneTree
var root_viewport = scene_tree.root.get_viewport_rid()
if disable_main:
# Disable main viewport so it doesn't redrawn
RenderingServer.viewport_set_active(root_viewport, false)
# Render SubViewport
for i in iterations:
await RenderingServer.frame_pre_draw
RenderingServer.viewport_set_update_mode(render.get_viewport_rid(), RenderingServer.VIEWPORT_UPDATE_ONCE)
RenderingServer.force_draw(true, 1.0 / iterations)
await RenderingServer.frame_post_draw
if disable_main:
# Enable main viewport again
RenderingServer.viewport_set_active(root_viewport, true)
await RenderingServer.frame_post_draw # image data doesn't updates correctly without this..
return subviewport.get_texture().get_image()
```
Left: expected. Right: result of multiple `force_draw()`, lighting didn't iterate and it always looks like the first iteration.
It only updates correclty when the main viewport is enabled during `force_draw()`.
But it slows down rendering since `force_draw()` draws all active viewports although I don't need the main viewport.
### Steps to reproduce
* Open the MRP. It contains the test project of the images above.
* Run the project. The left is a realtime `SubViewport`. The right creates a `SubViewport` dynamically, force draw multiple times and shows a `TextureRect` with the resulting image.
* Toggle "Disable main viewport".
* Rendering only looks correct when the main viewport is enabled.
### Minimal reproduction project (MRP)
[sdfgi-update.zip](https://github.com/user-attachments/files/17194488/sdfgi-update.zip)
| bug,topic:rendering,topic:3d | low | Major |
2,557,367,012 | flutter | [Scribe] Hover icon | ### Use case
Android's Scribe feature supports showing an icon when a stylus hovers over a field that supports Scribe handwriting input. Flutter should support this feature too.
### Proposal
The hover cursor can be set in `onResolvePointerIcon` in InputConnection in FlutterView.java. To know where the fields are that support Scribe, we'd likely have to send the rects over from the framework.
### See also
Scribe issue: https://github.com/flutter/flutter/issues/115607
Scribe support added in https://github.com/flutter/flutter/pull/148784 and https://github.com/flutter/engine/pull/52943. | a: text input,c: new feature,platform-android,engine,c: proposal,P1,team-text-input,triaged-text-input | medium | Minor |
2,557,376,889 | flutter | Document dirtying the source tree on CI (including `.gitignore`'d) has caching implications | _Forked from https://github.com/flutter/engine/pull/55475#issuecomment-2383597893:_
> CI does filesystem level caching, so even files that are .gitignored in the source tree may persist between CI runs
It is surprising and, with the exception of the [raw code in another repo](https://flutter.googlesource.com/recipes/+/refs/heads/main/recipe_modules/cache/api.py), undocumented behavior. We should document what the implications of this caching are, what types of errors or undefined behavior it can lead to, and what we expect tools and test authors to do (for example, using cleanup hooks to delete files, but perhaps more than that?) | engine,P2,c: tech-debt,team-engine,triaged-engine | low | Critical |
2,557,380,138 | PowerToys | App Hibernation Module | ### Description of the new feature / enhancement
Allows the user to "hibernate" an application. It will suspend the process + any subprocesses and hide it from the taskbar. There would then be some sort of UI which shows all of the hibernated apps and allows you to bring them back out of hibernation.
### Scenario when this would be used?
When you have a game open and you want to switch to doing something else without the game using up a load of resources, while still being able to return to it without needing to wait for it to boot up again.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,557,380,524 | pytorch | [user triton] error out with export/AOTI if dynamic shape is specialized at tl.constexpr | ### 🚀 The feature, motivation and pitch
If you're using PT2 with a custom triton kernel, and the custom triton kernel takes a tl.constexpr parameter, then we specialize the dynamic shape (https://github.com/pytorch/pytorch/pull/136512).
But for export/AOTI, that's not going to work: if the input really is dynamic, then you're going to run into issues at runtime. So we should make sure this is handled well, and error out.
### Alternatives
_No response_
### Additional context
_No response_
cc @ezyang @chauhang @penguinwu @bobrenjc93 @avikchaudhuri @gmagogsfm @zhxchen17 @tugsbayasgalan @angelayi @suo @ydwu4 @desertfire @chenyang78 @oulgen @aakhundov | triaged,oncall: pt2,module: dynamic shapes,export-triaged,oncall: export,module: aotinductor,module: user triton | low | Critical |
2,557,395,571 | flutter | Verify that `dart test` has acceptable semantics for engine CI | _Forked from https://github.com/flutter/engine/pull/55475_ some questions that shouldn't be buried on that PR.
I'm not sure what to do with this information (maybe there is an ask for the engine team to improve the infra or file downstream bugs?), but filing this for posterity to divorce it from merging https://github.com/flutter/engine/pull/55475 (which is unrelated to adding `dart test`, `dart test` already runs on engine CI).
---
> Does `dart test` do an implicit `pub get`?
Yes.
> Do we need a flag to skip implicit `pub get`s for `dart test`?
Unclear (based on the [discussion so far](https://github.com/flutter/engine/pull/55475)), leaning no.
> Does `dart test` write to the source tree at all?
Yes, since we consider `.gitignore`'d directories - `.dart_tool/test`.
> Do we need to isolate `dart test` in a way where it doesn't write to the source tree?
Unclear (based on the [discussion so far](https://github.com/flutter/engine/pull/55475)), leaning no.
> Does dart test send telemetry? Should we be explicitly disabling that on CI, somehow?
`package:unified_analytics` detect if we're running on CI and disable telemetry automatically
> Is it possible to ensure that no other process connects to a compilation server?
Yes, with [`--resident-compiler-info-file`](https://github.com/flutter/engine/pull/55475#issuecomment-2383903545) | engine,P2,c: tech-debt,team-engine,triaged-engine | low | Critical |
2,557,401,866 | ollama | Tool call support in Qwen 2.5 hallucinates with Maybe pattern | According to https://python.useinstructor.com/concepts/maybe/.
There is an issue with tool calling in a case like this:
```json
{
"messages": [
{
"role": "system",
"content": "Today's date is 2024-09-30. Please consider this when processing the availability information.\nIf you cannot extract the start date, use today.\nThis is the list of employees, with the initials, employee ID, full name, and skills:\n...\n\nDO NOT invent data. DO NOT hallucinate!"
},
{
"role": "user",
"content": "When does our colleague XYZ have two days available for a 2 days appointment?"
}
],
"model": "qwen2.5:7b-instruct-fp16",
"tool_choice": {
"type": "function",
"function": {
"name": "MaybeAvailabilityRequest"
}
},
"tools": [
{
"type": "function",
"function": {
"name": "MaybeAvailabilityRequest",
"description": "Correctly extracted `MaybeAvailabilityRequest` with all the required parameters with correct types",
"parameters": {
"$defs": {
"AvailabilityRequest": {
"properties": {
"personIds": {
"description": "List of person IDs to check availability for",
"items": {
"type": "integer"
},
"title": "Personids",
"type": "array"
},
"startDate": {
"description": "Start date for the availability check",
"title": "Startdate",
"type": "string"
},
"endDate": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "End date for the availability check",
"title": "Enddate"
},
"numberOfConsecutiveDays": {
"description": "Number of consecutive days required",
"title": "Numberofconsecutivedays",
"type": "integer"
}
},
"required": [
"personIds",
"startDate",
"endDate",
"numberOfConsecutiveDays"
],
"title": "AvailabilityRequest",
"type": "object"
}
},
"properties": {
"result": {
"anyOf": [
{
"$ref": "#/$defs/AvailabilityRequest"
},
{
"type": "null"
}
],
"default": null
},
"error": {
"default": false,
"title": "Error",
"type": "boolean"
},
"message": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Message"
}
},
"type": "object",
"required": []
}
}
}
]
}
```
it answers with this:
``` json
{
"id": "chatcmpl-485",
"object": "chat.completion",
"created": 1727721983,
"model": "qwen2.5:7b-instruct-fp16",
"system_fingerprint": "fp_ollama",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_oe8h5as1",
"type": "function",
"function": {
"name": "MaybeAvailabilityRequest",
"arguments": "{\"error\":false,\"message\":null,\"result\":{\"availableDateRange\":[{\"end_date\":\"2024-10-03\",\"start_date\":\"2024-10-01\"}]}}"
}
}
]
},
"finish_reason": "tool_calls"
}
],
"usage": {
"prompt_tokens": 477,
"completion_tokens": 158,
"total_tokens": 635
}
}
```
Which is obviously wrong and not following the JSON schema from the tool call.
When I use non function calling and craft the prompt manually, it always gets the answer right.
.cc @JianxinMa
Thanks! | feature request | low | Critical |
2,557,413,238 | pytorch | DISABLED test_open_device_registration (__main__.ExtensionBackendTests) | Platforms: linux, rocm, slow
This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_open_device_registration&suite=ExtensionBackendTests&limit=100) and the most recent trunk [workflow logs](https://github.com/pytorch/pytorch/runs/30857493223).
Over the past 3 hours, it has been determined flaky in 8 workflow(s) with 16 failures and 8 successes.
**Debugging instructions (after clicking on the recent samples link):**
DO NOT ASSUME THINGS ARE OKAY IF THE CI IS GREEN. We now shield flaky tests from developers so CI will thus be green but it will be harder to parse the logs.
To find relevant log snippets:
1. Click on the workflow logs linked above
2. Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work.
3. Grep for `test_open_device_registration`
4. There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs.
<details><summary>Sample error message</summary>
```
Traceback (most recent call last):
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 2147, in _run_ninja_build
subprocess.run(
File "/opt/conda/envs/py_3.9/lib/python3.9/subprocess.py", line 528, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v', '-j', '6']' returned non-zero exit status 1.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1764, in _jit_compile
_write_ninja_file_and_build_library(
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1876, in _write_ninja_file_and_build_library
_run_ninja_build(
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 2163, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error building extension 'extension_device'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/var/lib/jenkins/workspace/test/inductor/test_extension_backend.py", line 75, in setUpClass
cls.module = torch.utils.cpp_extension.load(
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1357, in load
return _jit_compile(
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1779, in _jit_compile
baton.release()
File "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/torch/utils/file_baton.py", line 50, in release
os.remove(self.lock_file_path)
FileNotFoundError: [Errno 2] No such file or directory: '/var/lib/jenkins/.cache/torch_extensions/py39_cpu/extension_device/lock'
```
</details>
Test file path: `inductor/test_extension_backend.py`
cc @clee2000 @ezyang @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire | triaged,module: flaky-tests,skipped,oncall: pt2,module: inductor | low | Critical |
2,557,413,242 | pytorch | DISABLED test_byte_tensor_assignment (__main__.TestAdvancedIndexing) | Platforms: mac, macos
This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_byte_tensor_assignment&suite=TestAdvancedIndexing&limit=100) and the most recent trunk [workflow logs](https://github.com/pytorch/pytorch/runs/30861081049).
Over the past 3 hours, it has been determined flaky in 3 workflow(s) with 3 failures and 3 successes.
**Debugging instructions (after clicking on the recent samples link):**
DO NOT ASSUME THINGS ARE OKAY IF THE CI IS GREEN. We now shield flaky tests from developers so CI will thus be green but it will be harder to parse the logs.
To find relevant log snippets:
1. Click on the workflow logs linked above
2. Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work.
3. Grep for `test_byte_tensor_assignment`
4. There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs.
<details><summary>Sample error message</summary>
```
Traceback (most recent call last):
File "/Users/ec2-user/runner/_work/pytorch/pytorch/test/test_mps.py", line 11657, in test_byte_tensor_assignment
self.assertEqual(len(w), 1)
File "/Users/ec2-user/runner/_work/_temp/conda_environment_11107079890/lib/python3.9/site-packages/torch/testing/_internal/common_utils.py", line 3889, in assertEqual
raise error_metas.pop()[0].to_error(
AssertionError: Scalars are not equal!
Expected 1 but got 2.
Absolute difference: 1
Relative difference: 1.0
To execute this test, run the following from the base repo dir:
python test/test_mps.py TestAdvancedIndexing.test_byte_tensor_assignment
This message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0
```
</details>
Test file path: `test_mps.py`
cc @clee2000 @malfet @albanD @kulinseth @DenisVieriu97 @jhavukainen | triaged,module: flaky-tests,module: macos,skipped,module: mps | low | Critical |
2,557,416,541 | flutter | Flavor API should be derived at the `flutter assemble` level so it is set correctly when run from native tooling, like Android Studio or Xcode | Currently, the app flavor is passed into the `FLUTTER_APP_FLAVOR` based on the `--flavor` flag passed into the Flutter tool, as implemented in https://github.com/flutter/flutter/pull/134179
https://github.com/flutter/flutter/blob/9441f9d48fce1d0b425628731dd6ecab8c8b0826/packages/flutter_tools/lib/src/runner/flutter_command.dart#L1341-L1352
However, that solution doesn't work when run from native tooling, like Android Studio of Xcode, which calls only into `flutter assemble`, so `FLUTTER_APP_FLAVOR` is unset.
The proposed community solution at https://github.com/flutter/website/issues/11178 for iOS/macOS requires `DART_DEFINES` to be individually set per Xcode scheme/config, which would be very easy to get out-of-sync, and essentially unnecessary given that `assemble` already has all the information it needs to parse which flavor should be used.
It would be better if the flavor parsing logic were pushed down into `assemble`. | platform-ios,tool,platform-mac,P2,team-tool,triaged-tool | low | Major |
2,557,492,864 | vscode | [macOS] Custom terminal not found on first launch | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.1
- OS Version: macOS Sonoma 14.5
We're using a custom terminal (provided by our extension) set as the default terminal in a .code-workspace. When launching VS Code, the wrong terminal is being used for the first terminal instance created. Every subsequent terminal is created using our custom terminal as expected. This can lead to issues when using our extension because we are providing environment variables to the terminal that are missing when the wrong terminal is used.
I've tried adjusting the extension activation settings and confirmed that the extension is indeed activating.
I am able to reproduce the same issue using the terminal-sample in the VS Code extension samples repo, so it doesn't appear to be specific to our extension.
I can only reproduce this issue on macOS - I could not reproduce on Windows 10.
Steps to Reproduce:
1. Clone the `terminal-sample` (https://github.com/microsoft/vscode-extension-samples/tree/main/terminal-sample).
2. Build and debug the sample.
3. Close the Terminal view, if open.
4. Create a workspace (`File > Save Workspace As...`) and save it anywhere.
5. In the workspace settings, set the custom terminal as the default:
```
"settings": {
"terminal.integrated.defaultProfile.osx": "Terminal API Profile",
}
```
6. Reload the debugged VS Code Window using the Command Palette (`Developer: Reload Window`)
7. Open the workspace settings and note the warning under the "Terminal API Profile":
<img width="1512" alt="Screenshot 2024-09-30 at 3 20 42 PM" src="https://github.com/user-attachments/assets/83c69b4e-3b29-45a9-b345-193b7ead1678">
8. Create a new terminal. This should use the "Terminal API Profile" by default, but it opens `zsh` instead.
9. Create another new terminal. The "Terminal API Profile" is correctly used.
| bug,terminal-profiles | low | Critical |
2,557,506,046 | langchain | KeyError: 'Field "metadata" does not exist in schema' | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
The DataFrame is in the following format.
```python
import lancedb
uri = "data/sample-lancedb"
db = lancedb.connect(uri,)
try:
table = db.create_table("movies",data=md_final)
except:
table = db.open_table("movies")
```
```python
from langchain.vectorstores import LanceDB
from langchain.chains import RetrievalQA
import os
from langchain_huggingface import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
docsearch = LanceDB(connection = db,
embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2"),
table_name="movies",
vector_key="vector",
id_key='title',
text_key='text',
uri=uri,
)
```
The error occurs in the following code.
```python
query = "I'm looking for an animated action movie. What could you suggest to me?"
docs = docsearch.similarity_search(query)
```
### Error Message and Stack Trace (if applicable)
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\langchain_community\vectorstores\lancedb.py:524, in LanceDB.similarity_search(self, query, k, name, filter, fts, **kwargs)
[500](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:500) def similarity_search(
[501](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:501) self,
[502](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:502) query: str,
(...)
[507](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:507) **kwargs: Any,
[508](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:508) ) -> List[Document]:
[509](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:509) """Return documents most similar to the query
[510](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:510)
[511](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:511) Args:
(...)
[522](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:522) List of documents most similar to the query.
[523](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:523) """
--> [524](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:524) res = self.similarity_search_with_score(
[525](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:525) query=query, k=k, name=name, filter=filter, fts=fts, score=False, **kwargs
[526](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:526) )
[527](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:527) return res
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\langchain_community\vectorstores\lancedb.py:498, in LanceDB.similarity_search_with_score(self, query, k, filter, **kwargs)
[496](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:496) embedding = self._embedding.embed_query(query)
[497](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:497) res = self._query(embedding, k, filter=filter, **kwargs)
--> [498](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:498) return self.results_to_docs(res, score=score)
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\langchain_community\vectorstores\lancedb.py:155, in LanceDB.results_to_docs(self, results, score)
[152](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:152) score_col = None
[154](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:154) if score_col is None or not score:
--> [155](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:155) return [
[156](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:156) Document(
[157](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:157) page_content=results[self._text_key][idx].as_py(),
[158](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:158) metadata=results["metadata"][idx].as_py(),
[159](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:159) )
[160](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:160) for idx in range(len(results))
[161](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:161) ]
[162](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:162) elif score_col and score:
[163](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:163) return [
[164](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:164) (
[165](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:165) Document(
(...)
[171](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:171) for idx in range(len(results))
[172](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:172) ]
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\langchain_community\vectorstores\lancedb.py:158, in <listcomp>(.0)
[152](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:152) score_col = None
[154](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:154) if score_col is None or not score:
[155](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:155) return [
[156](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:156) Document(
[157](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:157) page_content=results[self._text_key][idx].as_py(),
--> [158](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:158) metadata=results["metadata"][idx].as_py(),
[159](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:159) )
[160](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:160) for idx in range(len(results))
[161](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:161) ]
[162](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:162) elif score_col and score:
[163](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:163) return [
[164](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:164) (
[165](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:165) Document(
(...)
[171](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:171) for idx in range(len(results))
[172](file:///C:/Users/jefer/Documents/Livros/LLMs/BUILDING_LLM_POWERED_APPLICATIONS/Building-LLM-Powered-Applications/.conda/Lib/site-packages/langchain_community/vectorstores/lancedb.py:172) ]
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\pyarrow\table.pxi:1539, in pyarrow.lib._Tabular.__getitem__()
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\pyarrow\table.pxi:1625, in pyarrow.lib._Tabular.column()
File c:\Users\jefer\Documents\Livros\LLMs\BUILDING_LLM_POWERED_APPLICATIONS\Building-LLM-Powered-Applications\.conda\Lib\site-packages\pyarrow\table.pxi:1561, in pyarrow.lib._Tabular._ensure_integer_index()
KeyError: 'Field "metadata" does not exist in schema'
### Description
**I connected to the LanceDB database and tried to create a table called "movies" using the data from the md_final DataFrame. If the table already existed, I opened it. Then, I initialized an instance of LanceDB with the "sentence-transformers/all-MiniLM-L6-v2" embeddings model, configuring the vector key, ID key, and text key options. I defined a text query and called the similarity_search method to obtain the relevant documents.**
### System Info
```bash
System Information
------------------
> OS: Windows
> OS Version: 10.0.22631
> Python Version: 3.11.9 | packaged by Anaconda, Inc. | (main, Apr 19 2024, 16:40:41) [MSC v.1916 64 bit (AMD64)]
Package Information
-------------------
> langchain_core: 0.3.6
> langchain: 0.3.1
> langchain_community: 0.2.17
> langsmith: 0.1.129
> langchain_chroma: 0.1.4
> langchain_groq: 0.2.0
> langchain_huggingface: 0.1.0
> langchain_mistralai: 0.2.0
> langchain_openai: 0.2.1
> langchain_text_splitters: 0.3.0
Optional packages not installed
-------------------------------
> langgraph
> langserve
Other Dependencies
------------------
> aiohttp: 3.10.5
> async-timeout: Installed. No version info available.
> chromadb: 0.5.3
> dataclasses-json: 0.6.7
> fastapi: 0.115.0
> groq: 0.11.0
> httpx: 0.27.2
> httpx-sse: 0.4.0
> huggingface-hub: 0.24.7
> jsonpatch: 1.33
> numpy: 1.26.4
> openai: 0.28.0
> orjson: 3.10.7
> packaging: 23.2
> pydantic: 2.9.1
> PyYAML: 6.0.2
> requests: 2.32.3
> sentence-transformers: 3.1.1
> SQLAlchemy: 2.0.35
> tenacity: 8.5.0
> tiktoken: 0.7.0
> tokenizers: 0.19.1
> transformers: 4.44.2
> typing-extensions: 4.12.2
``` | Ɑ: vector store,investigate | low | Critical |
2,557,554,098 | vscode | API to access the shell type for a given terminal | Currently there is no API available on the terminal that allows extensions to detect the shell type. This is needed for Python where there are shell specific activation scripts. | feature-request,api,terminal,on-testplan,api-proposal | low | Major |
2,557,561,078 | pytorch | [inductor] requires_stride_order doesn't work with unbacked symints | ```py
import torch
from torch import Tensor
torch._dynamo.config.capture_dynamic_output_shape_ops = True
@torch.library.custom_op("mylib::foo", mutates_args={})
def foo(x: Tensor) -> Tensor:
return x.clone()
@foo.register_fake
def _(x):
u0 = torch.library.get_ctx().new_dynamic_size()
u1 = torch.library.get_ctx().new_dynamic_size()
u2 = torch.library.get_ctx().new_dynamic_size()
return x.new_empty(u0, u1, u2)
@torch.library.custom_op("mylib::bar", mutates_args={})
def bar(x: Tensor) -> Tensor:
return x.clone()
@bar.register_fake
def _(x):
return torch.empty_like(x)
x = torch.randn(2, 3, 4)
@torch.compile(fullgraph=True)
def f(x):
y = foo(x)
z = bar(y)
return z
f(x)
print("done")
```
In this case we should be able to infer the order of the sym strides (they are `u1 * u2, u2, 1`). Maybe we just need a sorting algorithm that understand unbacked symints
cc @ezyang @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @bdhirsh | triaged,module: custom-operators,oncall: pt2,module: dynamic shapes,module: inductor,module: pt2-dispatcher | low | Minor |
2,557,584,776 | deno | Deno test runs tests in workspace twice if test is not in a member | Title isn't quite accurate, it also only happens if you pass a path to deno test.
Repro:
```jsonc
// deno.jsonc
{
"workspace": [
"member"
]
}
```
```
❯ mkdir member; touch member/deno.json
```
```ts
// main_test.ts (in root of workspace)
Deno.test(function myCoolTest() {
console.log("running test...");
})
```
```
❯ deno test .
running 1 test from ./main_test.ts
myCoolTest ...
------- output -------
running test...
----- output end -----
myCoolTest ... ok (0ms)
running 1 test from ./main_test.ts
myCoolTest ...
------- post-test output -------
running test...
----- post-test output end -----
myCoolTest ... ok (0ms)
ok | 2 passed | 0 failed (11ms)
```
If you omit the `.` or the test is in `member`, this doesn't occur | bug,testing,workspaces | low | Critical |
2,557,591,356 | node | `assert.deepEqual()` report difference between promises during `test` | ### Version
v22.9.0
### Platform
```text
Linux regseblaptop 6.8.0-45-generic #45-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 30 12:02:04 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux
```
### Subsystem
Ubuntu 24.04.1 LTS
### What steps will reproduce the bug?
1. Create `test.mjs`
```javascript
import assert from "node:assert/strict";
import { mock, test } from "node:test";
test("promise", () => {
assert.deepEqual(Promise.resolve("foo"), Promise.resolve("foo"));
});
test("mock, promise and await", async () => {
const fn = mock.fn(() => "foo");
await fn(Promise.resolve("bar"));
assert.deepEqual(fn.mock.calls[0].arguments[0], Promise.resolve("bar"));
});
```
2. `node --test test.mjs`
### How often does it reproduce? Is there a required condition?
Always.
### What is the expected behavior? Why is that the expected behavior?
The `assert.deepEqual()` doesn't report difference between the two identical promises.
```
✔ promise (1.830551ms)
✔ mock, promise and await (0.533274ms)
ℹ tests 2
ℹ suites 0
ℹ pass 2
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 75.905452
```
### What do you see instead?
The `assert.deepEqual()` find difference between the two identical promises.
```
✖ promise (5.761508ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected
Promise {
'foo',
+ [Symbol(async_id_symbol)]: 39,
- [Symbol(async_id_symbol)]: 40,
[Symbol(trigger_async_id_symbol)]: 17
}
at TestContext.<anonymous> (file:///home/regseb/dev/tc/mock/test.mjs:5:12)
at Test.runInAsyncScope (node:async_hooks:211:14)
at Test.run (node:internal/test_runner/test:930:25)
at Test.start (node:internal/test_runner/test:829:17)
at startSubtestAfterBootstrap (node:internal/test_runner/harness:289:17) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: [Promise],
expected: [Promise],
operator: 'deepStrictEqual'
}
✖ mock, promise and await (0.791194ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected
Promise {
'bar',
+ [Symbol(async_id_symbol)]: 52,
+ [Symbol(trigger_async_id_symbol)]: 20
- [Symbol(async_id_symbol)]: 66,
- [Symbol(trigger_async_id_symbol)]: 54
}
at TestContext.<anonymous> (file:///home/regseb/dev/tc/mock/test.mjs:11:12)
at async Test.run (node:internal/test_runner/test:931:9)
at async Test.processPendingSubtests (node:internal/test_runner/test:629:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: [Promise],
expected: [Promise],
operator: 'deepStrictEqual'
}
ℹ tests 2
ℹ suites 0
ℹ pass 0
ℹ fail 2
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 82.541815
✖ failing tests:
test at test.mjs:4:1
✖ promise (5.761508ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected
Promise {
'foo',
+ [Symbol(async_id_symbol)]: 39,
- [Symbol(async_id_symbol)]: 40,
[Symbol(trigger_async_id_symbol)]: 17
}
at TestContext.<anonymous> (file:///home/regseb/dev/tc/mock/test.mjs:5:12)
at Test.runInAsyncScope (node:async_hooks:211:14)
at Test.run (node:internal/test_runner/test:930:25)
at Test.start (node:internal/test_runner/test:829:17)
at startSubtestAfterBootstrap (node:internal/test_runner/harness:289:17) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: [Promise],
expected: [Promise],
operator: 'deepStrictEqual'
}
test at test.mjs:8:1
✖ mock, promise and await (0.791194ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected
Promise {
'bar',
+ [Symbol(async_id_symbol)]: 52,
+ [Symbol(trigger_async_id_symbol)]: 20
- [Symbol(async_id_symbol)]: 66,
- [Symbol(trigger_async_id_symbol)]: 54
}
at TestContext.<anonymous> (file:///home/regseb/dev/tc/mock/test.mjs:11:12)
at async Test.run (node:internal/test_runner/test:931:9)
at async Test.processPendingSubtests (node:internal/test_runner/test:629:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: [Promise],
expected: [Promise],
operator: 'deepStrictEqual'
}
```
### Additional information
~~The problem only occurs in `test`.~~ https://github.com/nodejs/node/issues/55198#issuecomment-2384180276
1. Create `index.mjs`
```javascript
import assert from "node:assert/strict";
import { mock } from "node:test";
assert.deepEqual(Promise.resolve("foo"), Promise.resolve("foo"));
const fn = mock.fn(() => "foo");
await fn(Promise.resolve("bar"));
assert.deepEqual(fn.mock.calls[0].arguments[0], Promise.resolve("bar"));
```
2. `node index.mjs`
3. The `assert.deepEqual()` doesn't report difference between the two identical promises. :+1: | assert,promises,test_runner | medium | Critical |
2,557,600,127 | pytorch | Namespace error when using torch::unravel_index to implement a custom function in cuda. | ### 🚀 The feature, motivation and pitch
Thank you all for the great library.
I wanted to please ask wlease where is the unravel_index in located in the cpp source code of torch? since it seems it is not in the namespace ?
God bless
### Alternatives
_No response_
### Additional context
_No response_
cc @mruberry @rgommers | triaged,module: numpy | low | Critical |
2,557,611,784 | ui | [bug]: Tooltip have a problem with the index | ### Describe the bug
```
<Tooltip>
<TooltipTrigger className="w-full">
<Button variant="ghost" className="flex w-full justify-center gap-2">
<IconComponent className="h-4 w-4" />
</Button>
</TooltipTrigger>
<TooltipContent side="right">
<p>{text}</p>
</TooltipContent>
</Tooltip>
```
The problem is that it always stays below, even though I put a higher z-index
### Affected component/components
Tooltip
### How to reproduce
1. Clone component
2. Usage component
### Codesandbox/StackBlitz link
_No response_
### Logs
_No response_
### System Info
```bash
Windows, Arc and Brave
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,557,651,202 | PowerToys | Sort Pattern and Replace-With lists by most recently used | ### Description of the new feature / enhancement
Sort the "Pattern" and "Replace With" drop-down history lists by most recently used, rather than the current sort which seems random.
### Scenario when this would be used?
At times I am going back and forth between a small number of patterns/filenames. It'd be nice to have my more recently-used items near the top of the history lists instead of randomly distributed (or even disappearing) from the lists.
### Supporting information
N/A | Needs-Triage | low | Minor |
2,557,678,038 | vscode | `inlineChat.viewInChat` command from notebook will cause pylance to crash | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes/No
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.1
- OS Version: Windows 11 Enterprise Version 24H2 (OS Build 26100.1742)
Steps to Reproduce:
1. Install Python and Pylance extensions
2. Open a notebook or create a notebook file with the following content, and press `ctrl + i` to open the copilot inline chat
```python
# notebook1.ipynb
def foo():
print("foo")
```
3. Ask for a code change, then run inlineChat.viewInChat on the response (ctrl+down)
4. Pylance crashes with bad request
```
2024-09-30 14:25:21.458 [info] [Error - 2:25:21 PM] Request textDocument/documentSymbol failed.
2024-09-30 14:25:21.458 [info] Message: Request textDocument/documentSymbol failed with message: Debug Failure. Notebook file should not be passed to getWorkspaceForFile: vscode-chat-code-block:/c%3A/Users/stellahuang/source/projects/issue6427/notebook1.ipynb?6ff16a3c-1351-4aff-837f-d29e7cb883a7
Code: -32603
```
When inspecting the [textDocument/documentSymbol](https://microsoft.github.io/language-server-protocol/specifications/lsp/3.17/specification/#textDocument_documentSymbol) request from the Pylance side, I noticed that the `DocumentSymbolParams.textDocument.uri = 'vscode-chat-code-block:/c%3A/Users/stellahuang/source/projects/issue6427/notebook1.ipynb?3574a4e6-6692-4217-86b1-0ca8750d25f6'`. It looks like the query is for the notebook file itself, not for a specific cell, which seems like a bug.
Related bug opened in Pylance: https://github.com/microsoft/pylance-release/issues/6454 | under-discussion,notebook,inline-chat | low | Critical |
2,557,678,204 | flutter | [A11y] Prelaunch report and internal android a11y testing framework can work with Flutter | ### Use case
Currently the PDC prelaunch report skips Flutter app in all android version.
Pre API 34, all warning are muted
Post API 34, PDC isn't able to read into Flutter ANI and produce a useful report.
there isn't anything we can do about pre 34 because Android doesn't provide an API to look into virtual view, but we should make sure post API 34 the PDC can correctly identify issues in Flutter apps.
### Proposal
make sure internal a11y testing framework can run on flutter post API 34 | P2,fyi-android,team-accessibility,triaged-accessibility | low | Minor |
2,557,734,894 | flutter | Support iOS targets in `et run` | `et run` (which builds the engine, and passes `--local-engine` flags to `flutter run`) does not support iOS.
Besides finding a champion that regularly builds and debugs iOS engines to help develop (and dogfood) this workflow, we also might have assumptions in `et` that don't hold for iOS builds. For example, [`<RunTarget>.buildConfigFor`](https://github.com/flutter/engine/blob/bd36636b9a83dfdbb7ef4a0c8fa9ad66f04c7625/tools/engine_tool/lib/src/run_utils.dart#L44-L55) makes an assumption about a 1:1 mapping from a target platform to an engine build:
```dart
String buildConfigFor(String mode) {
switch (targetPlatform) {
case 'android-arm64':
return 'android_${mode}_arm64';
case 'darwin':
return 'host_$mode';
case 'web-javascript':
return 'chrome_$mode';
default:
throw UnimplementedError('No mapping for $targetPlatform');
}
}
```
However, for iOS, there isn't such a 1:1 mapping, as there are separate builds for an iOS simulator or device.
`RunTarget` would need to be expanded to receive both the `TargetPlatform` _and_ [`emulator`](https://github.com/flutter/flutter/blob/9441f9d48fce1d0b425628731dd6ecab8c8b0826/packages/flutter_tools/lib/src/device.dart#L899) key. | platform-ios,P3,team-engine,triaged-engine,e: engine-tool | low | Critical |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.