MedPod GP 3.2.1

.gitattributes

@@ -83,3 +83,4 @@ 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
+medpodgp-3.2.1-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:c5142d0d0646d7009e32f4c5650d15aeed2199866c178237607338e58de6df1d
-size 458642
+oid sha256:0e8cdd9f5078cb4263df202fa9c40ff29f2ab31fd8c63f9a3484d3cb2ac27bcd
+size 458633

LICENSE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfbf4272f193f7b34140a937a750864b5d0d187242f4cace6c12ef293e6717d6
-size 60436
+oid sha256:52f1d61e8505857780095bc37f9dab24df05a2e54134ddd1241e1e66430554de
+size 60432

PRODUCT_INFORMATION.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a9ede82bb45090200a1432582566c85559f816ce78ece5239a09c021bf9885
-size 696479
+oid sha256:9a34cf436e260f1a6b30ab4c7f012dd1adf26711dd940bef436dd25751bfa278
+size 698009

README.md

@@ -35,7 +35,10 @@ 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 3.2.0** — native on **macOS, Windows and Linux**. New in 3.2:
+> 🎉 **Latest release: MedPod GP 3.2.1** — native on **macOS, Windows and Linux**. New in 3.2.1:
+> **speech recognition entirely on the NVIDIA card** (75 s of speech ready about 2 s after
+> stop on an RTX laptop) and **far less memory on Windows** (a recording 3.5 GB instead of 9.6,
+> an X-ray 4.9 GB instead of 7.5). 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,
@@ -85,9 +88,9 @@ The same app, with the same interface, on all three systems — native on each,
 
 | Your computer | Download | Install |
 |---|---|---|
-| 🍎 **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) |
+| 🍎 **Mac** — Apple silicon (M1 or later), macOS 13+ | [**medpodgp-3.2.1-macos-arm64.dmg**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.1-macos-arm64.dmg) | Open it and drag **MedPod GP** to **Applications** |
+| 🪟 **Windows 10/11** (64-bit) | [**medpodgp-3.2.1-windows-x64.zip**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.1-windows-x64.zip) | Unzip anywhere and double-click **`medpodgp.exe`** — no installer |
+| 🐧 **Linux** (x86-64, glibc 2.31+) | [**medpodgp-3.2.1-linux-x64.tar.gz**](https://huggingface.co/cloudkites/medpodgp/resolve/main/medpodgp-3.2.1-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)
@@ -161,6 +164,22 @@ models) with its tokenizer and, for MedGemma, its image encoder.
   NVIDIA graphics card on Windows (driver only), every core of a processor otherwise;
   light and dark themes.
 
+## 🎉 What's new in 3.2.1
+
+- **Speech on the NVIDIA card from start to finish** — in 3.2 the recognizer heard the
+  recording on the graphics card but wrote the text on the processor; now both run on the
+  card. On an RTX 2000 Ada laptop 75 s of speech is ready in **4.5 s instead of 11 s**,
+  loading included, and the recognizer now **loads while you record**, so the text follows
+  the stop button by about 2 s.
+- **Far less memory on Windows** — the recognizer and the image encoder each held their
+  weights twice (in the computer's memory and on the card, which Windows charges to the
+  computer too) and kept memory they had finished with. A recording on the card now needs
+  **3.5 GB** of Windows' committed memory (9.6 GB in 3.2.0), an X-ray **4.9 GB** (7.5), and
+  speech on the processor 4.1 GB (7.6), so the language model steps aside far less often.
+- **Lighter everywhere** — the recognizer loads in about half the time, and every system
+  needs less memory: 75 s of speech 7.5 GB on the Mac (11.2 in 3.2.0) and 3.7 GB on Linux
+  (6.0); an X-ray 5.6 GB on the Mac (7.5).
+
 ## 🎉 What's new in 3.2
 
 - **Windows runs the AI on the NVIDIA graphics card** — many clinical laptops have one.
@@ -229,14 +248,15 @@ chest X-ray report, and transcription of 75 s of speech:
 | | 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 the summary starts | 0.2 s | 2.2 s | 7.3 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 |
+| X-ray: reading the image | 1.1 s | 10 s | 32 s | 4.6 s |
+| 75 s of speech transcribed in | 1.4 s | 5.2 s | 13 s | 4.5 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
+is short of memory. Speech times include loading the recognizer, which in the app happens
+during the recording (on an NVIDIA card the text is ready about 2 s after stop). 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.
 

USER_GUIDE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b5cd23be24c195d4ab82e18535898509219959764dda7cfbbd05756b53b4da
-size 10824995
+oid sha256:e46705366b3d27d6a7a25db1dd22cd192c5b6f06db687043070dc6ff2010f406
+size 10825052

medpodgp-3.2.0-macos-arm64.dmg.sha256

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

medpodgp-3.2.0-windows-x64.zip.sha256

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

medpodgp-3.2.0-linux-x64.tar.gz → medpodgp-3.2.1-linux-x64.tar.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfa7ee7a0adec4acf01819fdd38ca8291a3a7476c84097b6f0763a79ad139c5
-size 79022682
+oid sha256:aa385e614ec3efc7bc586ea9fdd6624c16818e1427e2856971bb0fa603763f3a
+size 78993753

medpodgp-3.2.0-linux-x64.tar.gz.sha256 → medpodgp-3.2.1-linux-x64.tar.gz.sha256

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e704e11af45fb7455211c3326aa90e7bd59564d87ef59ab01a5e5effc6343297
+oid sha256:34dd1a85b4b3c092e5e866093057173a727f8f365efacb9a5ce8afcffb4566b6
 size 98

medpodgp-3.2.0-macos-arm64.dmg → medpodgp-3.2.1-macos-arm64.dmg

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900bb325f5114d49928d5e1acd309b72aa6925a8e2b0a34efdc979f50a5cc2cf
-size 74798574
+oid sha256:bfd82bd6eb1ef81b9a0b3bf2423d334ddcb8aba8facd98d8480197ecb6b94d41
+size 74800724

medpodgp-3.2.1-macos-arm64.dmg.sha256

@@ -0,0 +1 @@
+bfd82bd6eb1ef81b9a0b3bf2423d334ddcb8aba8facd98d8480197ecb6b94d41  medpodgp-3.2.1-macos-arm64.dmg

medpodgp-3.2.0-windows-x64.zip → medpodgp-3.2.1-windows-x64.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2984ae6893cabf5b0533cc63a7a1bed76c0f03a76688dc073babfd5b62e20302
-size 95783284
+oid sha256:4547b891c8e119a1ef8353e0261e9a0475cf0d30a8cdba7d4ddd33fdfbed0a4e
+size 95890129

medpodgp-3.2.1-windows-x64.zip.sha256

@@ -0,0 +1 @@
+4547b891c8e119a1ef8353e0261e9a0475cf0d30a8cdba7d4ddd33fdfbed0a4e  medpodgp-3.2.1-windows-x64.zip