MedPod GP 3.2.0

.gitattributes

@@ -82,3 +82,4 @@ demo/medpodgp-3.1-macos.mp4 filter=lfs diff=lfs merge=lfs -text
 demo/medpodgp-3.1-windows.mp4 filter=lfs diff=lfs merge=lfs -text
 medpodgp-3.1.0-macos-arm64.dmg filter=lfs diff=lfs merge=lfs -text
 medpodgp-3.1.1-macos-arm64.dmg filter=lfs diff=lfs merge=lfs -text
+medpodgp-3.2.0-macos-arm64.dmg filter=lfs diff=lfs merge=lfs -text

DOWNLOAD_INSTALL_GUIDE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e490100142d66a547f2f22d0d5e230eebd8c8a9e0e4f1ed959807fc7941776e4
-size 457927
+oid sha256:c5142d0d0646d7009e32f4c5650d15aeed2199866c178237607338e58de6df1d
+size 458642

LICENSE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63704046f2cab06901fa8fbc41fc94a4ce0dc245fcfb58316de8b19fdc45f78
-size 60426
+oid sha256:bfbf4272f193f7b34140a937a750864b5d0d187242f4cace6c12ef293e6717d6
+size 60436

PRODUCT_INFORMATION.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d3d46b9e52083e7d2d17a792c6422446aaf3db9efac7c3a43ac1e75f021995
-size 688993
+oid sha256:38a9ede82bb45090200a1432582566c85559f816ce78ece5239a09c021bf9885
+size 696479

README.md

@@ -35,11 +35,13 @@ A product of **CloudKites AI Lab (CloudKites Pty Ltd)**, Sydney, Australia.
 > output must be reviewed and verified by a qualified clinician. See **Medical
 > disclaimer & intended use** below.
 
-> 🎉 **Latest release: MedPod GP 3.1.1** — native on **macOS, Windows and Linux**, with
-> **MedSearch knowledge packs included** (CloudKites' summaries of eTG, AMH and Australian
-> guidelines), **speech recognition about seven times faster** on Windows and Linux,
-> **every Ask AI sentence cited**, and — new in 3.1.1 — **sharper MedSearch**: Ask AI reads
-> only the sources that match the question. The previous edition,
+> 🎉 **Latest release: MedPod GP 3.2.0** — native on **macOS, Windows and Linux**. New in 3.2:
+> **Windows uses the NVIDIA graphics card** (display driver only, nothing else to install —
+> about 10× faster answers and X-rays than 3.1 on an RTX laptop), **nearly twice as fast on a
+> Windows processor**, Qwen3.5 reading requests 8–10× faster, instant follow-up questions,
+> and **MedSearch that understands everyday words and abbreviations** ("water infection",
+> "AF", "piles"). MedSearch knowledge packs (CloudKites' summaries of eTG, AMH and Australian
+> guidelines) are included. The previous edition,
 > [MedPod GP 2.0](#-previous-edition-medpod-gp-20-windows) (Windows), is still available.
 
 > 📘 **New to MedPod GP? Start with the [User Guide (PDF)](https://huggingface.co/cloudkites/medpodgp/resolve/main/USER_GUIDE.pdf).**
@@ -76,16 +78,16 @@ the window's own content, recorded by the app.
 
 ---
 
-## ⬇️ Download MedPod GP 3.1 — pick your computer
+## ⬇️ Download MedPod GP 3.2 — pick your computer
 
 The same app, with the same interface, on all three systems — native on each, with
 **no runtime dependencies** (nothing else to install).
 
 | Your computer | Download | Install |
 |---|---|---|
-| 🍎 **Mac** — Apple silicon (M1 or later), macOS 13+ | [**medpodgp-3.1.1-macos-arm64.dmg**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.1.1-macos-arm64.dmg) | Open it and drag **MedPod GP** to **Applications** |
-| 🪟 **Windows 10/11** (64-bit) | [**medpodgp-3.1.1-windows-x64.zip**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.1.1-windows-x64.zip) | Unzip anywhere and double-click **`medpodgp.exe`** — no installer |
-| 🐧 **Linux** (x86-64, glibc 2.31+) | [**medpodgp-3.1.1-linux-x64.tar.gz**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.1.1-linux-x64.tar.gz) | Extract, then `./install.sh` (or run `./medpodgp` in place) |
+| 🍎 **Mac** — Apple silicon (M1 or later), macOS 13+ | [**medpodgp-3.2.0-macos-arm64.dmg**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.0-macos-arm64.dmg) | Open it and drag **MedPod GP** to **Applications** |
+| 🪟 **Windows 10/11** (64-bit) | [**medpodgp-3.2.0-windows-x64.zip**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.0-windows-x64.zip) | Unzip anywhere and double-click **`medpodgp.exe`** — no installer |
+| 🐧 **Linux** (x86-64, glibc 2.31+) | [**medpodgp-3.2.0-linux-x64.tar.gz**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.0-linux-x64.tar.gz) | Extract, then `./install.sh` (or run `./medpodgp` in place) |
 
 Every file has a matching **`.sha256`**, and
 [**`SHA256SUMS`**](https://huggingface.co/cloudkites/medpodgp/resolve/main/SHA256SUMS)
@@ -155,8 +157,34 @@ models) with its tokenizer and, for MedGemma, its image encoder.
   it, or export **PDF, Word, Markdown or text**.
 - **🔐 For the whole practice** — local accounts (owner, administrators,
   clinicians), private notes, automatic lock, an audit log of who did what.
-- **💻 Native everywhere** — one app on macOS, Windows and Linux; the Mac's GPU,
-  every core of a Windows or Linux processor; light and dark themes.
+- **💻 Native everywhere** — one app on macOS, Windows and Linux; the Mac's GPU, an
+  NVIDIA graphics card on Windows (driver only), every core of a processor otherwise;
+  light and dark themes.
+
+## 🎉 What's new in 3.2
+
+- **Windows runs the AI on the NVIDIA graphics card** — many clinical laptops have one.
+  Nothing extra to install: the display driver is enough (the GPU programs are built into
+  MedPod GP, which stays one signed `.exe`). On an RTX 2000 Ada laptop: answers at
+  **71 tokens/s instead of 7.5**, a consultation transcript read in **0.4 s instead of 11 s**,
+  a chest X-ray read in **under 5 s instead of 57 s**. Without such a card the processor takes over
+  by itself.
+- **Nearly twice as fast on a Windows processor** — Windows 11's efficiency mode was slowing
+  MedPod GP down; it now asks to run at full speed: 13 tokens/s on the laptop's processor
+  (7.5), an X-ray in 32 s (57), 75 s of speech in 14 s (23).
+- **Qwen3.5 reads requests 8–10× faster on processors** (in one batch instead of a token at
+  a time), and **follow-up questions start in a fraction of a second** on every computer.
+- **Memory leaks fixed** — each image used to leave 1.7 GB behind, and each transcription
+  on the processor about 300 MB (some thirty recordings ran a Windows laptop out of memory).
+- **Memory planned on Windows** — Windows counts the graphics card's memory against the
+  computer's own; MedPod GP checks what is left before an image or a recording and, when
+  it is short, sets the language model aside for a moment instead of failing.
+- **MedSearch understands how GPs write** — "water infection", "piles", "AF", "blood
+  thinner", "pink eye" and 100+ other everyday phrases and abbreviations find the pages
+  that say "urinary tract infection", "haemorrhoids", "atrial fibrillation",
+  "anticoagulant", "conjunctivitis"; US spellings find the Australian ones; "cervical"
+  means the cervix with *screening* and the neck with *radiculopathy*. On held-out
+  questions the first result is relevant **95% of the time (76% in 3.1.1)**.
 
 ## 🎉 What's new in 3.1.1
 
@@ -198,14 +226,17 @@ models) with its tokenizer and, for MedGemma, its image encoder.
 MedGemma 1.5 4B summarising a consultation transcript (~550 tokens in, 300 out), a
 chest X-ray report, and transcription of 75 s of speech:
 
-| | Mac (M5 Pro, GPU) | Linux (Ryzen 9 9955HX, CPU) | Windows laptop (Core i7-13800H, CPU) |
-|---|---|---|---|
-| Writing speed | 87 tok/s | 18 tok/s | 7.5 tok/s |
-| Wait before the summary starts | 0.2 s | 1.9 s | 11 s |
-| X-ray: reading the image | 1.2 s | 9.4 s | 57 s |
-| 75 s of speech transcribed in | 2.3 s | 5.7 s | 23 s |
-
-People read about 5–7 tokens a second, so answers keep pace with reading on every
+| | Mac (M5 Pro, GPU) | Linux (Ryzen 9 9955HX, CPU) | Windows laptop (i7-13800H, CPU) | Windows laptop (RTX 2000 Ada) |
+|---|---|---|---|---|
+| Writing speed | 87 tok/s | 19 tok/s | 13 tok/s | 71 tok/s |
+| Wait before the summary starts | 0.2 s | 2.0 s | 7.1 s | 0.4 s |
+| Wait before a follow-up answer | 0.06 s | 0.1 s | 0.4 s | 0.2 s |
+| X-ray: reading the image | 1.3 s | 11 s | 32 s | 4.9 s |
+| 75 s of speech transcribed in | 2.3 s | 5.9 s | 14 s | 11 s |
+
+The Windows GPU column is the display driver alone, as a GP's PC has it; its X-ray time
+includes setting the language model aside for a moment, which MedPod GP does when Windows
+is short of memory (3.6 s with the model kept). People read about 5–7 tokens a second, so answers keep pace with reading on every
 machine measured, and every one transcribes faster than the recording plays. The
 Product Information PDF has the full charts.
 
@@ -215,12 +246,13 @@ Product Information PDF has the full charts.
 |---|---|---|---|
 | System | macOS 13+ | Windows 10 or 11, 64-bit | glibc 2.31+ (Ubuntu 20.04+, Debian 11+, Fedora 32+) |
 | Processor | Apple M1 or later | AVX2 (Intel 2013+, AMD 2015+) | AVX2 |
+| Graphics | (the Mac's own GPU) | optional: an NVIDIA GeForce RTX 20 series or newer / RTX workstation card (6 GB for images), display driver only | — |
 | Memory | 16 GB (8 GB with Qwen3.5 2B) | 16 GB | 16 GB |
 | Disk | 8 GB for MedGemma + speech | 8 GB | 8 GB |
 
 ## 📚 MedSearch knowledge packs
 
-Three packs come inside every 3.1 download — nothing to install:
+Three packs come inside every download — nothing to install:
 
 | Pack | Summarises | Sources | Sections |
 |---|---|---|---|

USER_GUIDE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90691b5ac8e86c97c91167840daa1bb37c39337078b6c427a6a159e64508af9f
-size 10823112
+oid sha256:b6b5cd23be24c195d4ab82e18535898509219959764dda7cfbbd05756b53b4da
+size 10824995

medpodgp-3.1.1-macos-arm64.dmg.sha256

@@ -1 +0,0 @@
-ff68b46380719af8d917a1fe84fbada982c25ccb192979085c637fd314d5b336  medpodgp-3.1.1-macos-arm64.dmg

medpodgp-3.1.1-windows-x64.zip.sha256

@@ -1 +0,0 @@
-f945e94d6db4da3461d953653433364bdcd987cdbfdf1dcdbe76f2d20b21b576  medpodgp-3.1.1-windows-x64.zip

medpodgp-3.1.1-linux-x64.tar.gz → medpodgp-3.2.0-linux-x64.tar.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d9bfc5e1c1aa02d2acb591aa70874ad0c12cd6990de16c7d13bb54afd91d5d
-size 78865919
+oid sha256:1cfa7ee7a0adec4acf01819fdd38ca8291a3a7476c84097b6f0763a79ad139c5
+size 79022682

medpodgp-3.1.1-linux-x64.tar.gz.sha256 → medpodgp-3.2.0-linux-x64.tar.gz.sha256

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd23cb98462df7cd8511f16b2b88548254aaa5248eda2acb0c7fd1baf0ff10b3
+oid sha256:e704e11af45fb7455211c3326aa90e7bd59564d87ef59ab01a5e5effc6343297
 size 98

medpodgp-3.1.1-macos-arm64.dmg → medpodgp-3.2.0-macos-arm64.dmg

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff68b46380719af8d917a1fe84fbada982c25ccb192979085c637fd314d5b336
-size 74662744
+oid sha256:900bb325f5114d49928d5e1acd309b72aa6925a8e2b0a34efdc979f50a5cc2cf
+size 74798574

medpodgp-3.2.0-macos-arm64.dmg.sha256

@@ -0,0 +1 @@
+900bb325f5114d49928d5e1acd309b72aa6925a8e2b0a34efdc979f50a5cc2cf  medpodgp-3.2.0-macos-arm64.dmg

medpodgp-3.1.1-windows-x64.zip → medpodgp-3.2.0-windows-x64.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f945e94d6db4da3461d953653433364bdcd987cdbfdf1dcdbe76f2d20b21b576
-size 78542890
+oid sha256:2984ae6893cabf5b0533cc63a7a1bed76c0f03a76688dc073babfd5b62e20302
+size 95783284

medpodgp-3.2.0-windows-x64.zip.sha256

@@ -0,0 +1 @@
+2984ae6893cabf5b0533cc63a7a1bed76c0f03a76688dc073babfd5b62e20302  medpodgp-3.2.0-windows-x64.zip