mlboydaisuke commited on
Commit
cc7ef72
·
verified ·
1 Parent(s): 025e16e

Note b2 (beta3-loadable) bundles under gpu-pipelined-b2/

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -14,6 +14,14 @@ tags:
14
 
15
  # Youtu-LLM-2B — Apple Core AI (`.aimodel`)
16
 
 
 
 
 
 
 
 
 
17
  [Youtu-LLM-2B](https://huggingface.co/tencent/Youtu-LLM-2B) (Tencent) converted to Apple
18
  **Core AI** for iOS 27 / macOS 27 (beta) — the **[zoo](https://github.com/john-rocky/coreai-model-zoo)'s
19
  first Multi-head Latent Attention (MLA) model that runs on iPhone**, and its first **dense**
 
14
 
15
  # Youtu-LLM-2B — Apple Core AI (`.aimodel`)
16
 
17
+ > [!NOTE]
18
+ > **Update 2026-07-15:** `gpu-pipelined-b2/` adds `youtu_llm_2b_decode_absorbed_int8_msdpa_g32` re-exported with
19
+ > `coreai-core 1.0.0b2`, loadable on the OS 27 **beta 3** toolchain (June-era b1
20
+ > bundles fail to load there with a versioned-IR error). The original b1 tree is
21
+ > retained unchanged so existing apps and pinned catalogs keep working. The b2
22
+ > decode bundle is the exact artifact measured on [DeviceMark](https://devicemark.github.io/).
23
+
24
+
25
  [Youtu-LLM-2B](https://huggingface.co/tencent/Youtu-LLM-2B) (Tencent) converted to Apple
26
  **Core AI** for iOS 27 / macOS 27 (beta) — the **[zoo](https://github.com/john-rocky/coreai-model-zoo)'s
27
  first Multi-head Latent Attention (MLA) model that runs on iPhone**, and its first **dense**