Add v75 arch section to README

README.md

@@ -14,41 +14,35 @@ language:
   - en
 ---
 
-# InternVL3.5-1B — QHexRT NPU bundle (Hexagon v79)
+# InternVL3.5-1B — QHexRT NPU bundle
 
-Precompiled **InternVL3.5-1B** vision-language model for the **QHexRT** runtime on Qualcomm
-Hexagon **v79** (Snapdragon 8 Elite / SM8750, e.g. Galaxy S25). Image → caption runs **entirely on
-the NPU**: the InternViT-300M vision encoder and the full Qwen3-0.6B language model are
-`qnn_context_binary` graphs; the host does only light glue (image resize, patch-embed, pixel-shuffle
-projector, tokenize/splice, sampling). Device-validated end-to-end on diverse photos.
+Precompiled **InternVL3.5-1B** vision-language model for the **QHexRT** runtime on Qualcomm Hexagon NPU.
+Image → caption runs **entirely on the NPU**: the InternViT-300M vision encoder and the full Qwen3-0.6B
+language model are `qnn_context_binary` graphs; the host does only light glue (image resize, patch-embed,
+pixel-shuffle projector, tokenize/splice, sampling). Device-validated end-to-end on diverse photos.
 
 The model is driven by QHexRT's declarative **manifest plan-interpreter** (`Session::generate` via the
 `internvl_generate` host-op) — the same engine that runs the other `*_HNPU` bundles.
 
-## Contents (`v79/`)
-| file | what | size |
-|------|------|------|
-| `internvl3_5-1b-512.json` | QHexRT manifest (vlm family, `internvl_generate` plan) | — |
-| `ivl_enc2.bin` | InternViT-300M vision encoder — 24-layer, **fp16**, 2D `[seq,dim]` I/O | 621 MB |
-| `ivl_pf_512.bin` | Qwen3-0.6B **batched prefill** graph, AR=512 (padded) — **arbitrary prompts** up to ~256 text tokens (**fp16**) | 890 MB |
-| `ivl_dec_w4.bin` | Qwen3-0.6B **decode** step (1 token), **W4A16** | 225 MB |
-| `ivl_lmh_q.bin` | untied **lm-head**, **W8A16** (int8) → logits over 151936 vocab | 158 MB |
-| `ivl_embed_f16.bin` | token embedding table `[151936,1024]` f16 (mmap, host lookup) | 311 MB |
-| `tokenizer.json` | Qwen3 tokenizer (vocab 151936) | 11 MB |
-| `vlm/` | host vision preproc: Conv2d patch-embed, pos-embed, layer-norm + pixel-shuffle MLP projector, prompt template | 27 MB |
+Context binaries are **arch-pinned** — pick the sibling dir that matches your device.
 
-Total ≈ **2.25 GB** on disk; ≈ **2.0 GB** peak device RSS at runtime (weights are ion-shared host↔DSP,
-not duplicated).
+## Architectures
+
+| Dir | Device (example) | Status |
+|-----|------------------|--------|
+| `v79/` | Galaxy S25 / SM8750 (Hexagon v79) | Device-validated |
+| `v81/` | SM8850 (Hexagon v81) | Device-validated |
+| `v75/` | Galaxy S24 / SM8650 (Hexagon v75) | Device-validated |
 
 ## Run (QHexRT CLI)
 ```bash
 hf download runanywhere/internvl3_5_1b_HNPU --local-dir internvl3_5_1b_HNPU
-# qhx_generate comes from a QHexRT build; QNN libs from the QAIRT SDK (lib/aarch64-android) + v79 HTP skel.
-adb push internvl3_5_1b_HNPU/v79 /data/local/tmp/wq/internvl
+# qhx_generate from a QHexRT build; QNN libs from QAIRT SDK (lib/aarch64-android) + matching HTP skel.
+adb push internvl3_5_1b_HNPU/v79 /data/local/tmp/wq/internvl   # or v75/ or v81/
 adb push my_photo.jpg /data/local/tmp/wq/internvl/
 
-adb shell "cd /data/local/tmp/wq && LD_LIBRARY_PATH=. ADSP_LIBRARY_PATH=. \
-  ./qhx_generate internvl/internvl3_5-1b-512.json libQnnHtp.so libQnnSystem.so internvl \
+adb shell "cd /data/local/tmp/wq && export ADSP_LIBRARY_PATH='/data/local/tmp/wq/dsp;/data/local/tmp/wq;/vendor/dsp/cdsp'; \
+  LD_LIBRARY_PATH=. ./qhx_generate internvl/internvl3_5-1b-512.json libQnnHtp.so libQnnSystem.so internvl \
   60 'What animals are in this picture and what are they doing?' internvl/my_photo.jpg"
 # -> text: "In the image, there are two cats lying on a pink couch ..."
 ```
@@ -57,6 +51,21 @@ adb shell "cd /data/local/tmp/wq && LD_LIBRARY_PATH=. ADSP_LIBRARY_PATH=. \
 - **Arbitrary prompts**: the padded `AR=512` prefill accepts any prompt up to ~256 text tokens (image is
   fixed at 256 tokens). Ask real questions, not just a fixed caption string.
 
+## Contents (`v79/`)
+| file | what | size |
+|------|------|------|
+| `internvl3_5-1b-512.json` | QHexRT manifest (vlm family, `internvl_generate` plan) | — |
+| `ivl_enc2.bin` | InternViT-300M vision encoder — 24-layer, **fp16**, 2D `[seq,dim]` I/O | 621 MB |
+| `ivl_pf_512.bin` | Qwen3-0.6B **batched prefill** graph, AR=512 (padded) — **arbitrary prompts** up to ~256 text tokens (**fp16**) | 890 MB |
+| `ivl_dec_w4.bin` | Qwen3-0.6B **decode** step (1 token), **W4A16** | 225 MB |
+| `ivl_lmh_q.bin` | untied **lm-head**, **W8A16** (int8) → logits over 151936 vocab | 158 MB |
+| `ivl_embed_f16.bin` | token embedding table `[151936,1024]` f16 (mmap, host lookup) | 311 MB |
+| `tokenizer.json` | Qwen3 tokenizer (vocab 151936) | 11 MB |
+| `vlm/` | host vision preproc: Conv2d patch-embed, pos-embed, layer-norm + pixel-shuffle MLP projector, prompt template | 27 MB |
+
+Total ≈ **2.25 GB** on disk; ≈ **2.0 GB** peak device RSS at runtime (weights are ion-shared host↔DSP,
+not duplicated).
+
 ## Performance (measured, v79 / S25)
 | stage | time |
 |-------|------|
@@ -67,20 +76,41 @@ adb shell "cd /data/local/tmp/wq && LD_LIBRARY_PATH=. ADSP_LIBRARY_PATH=. \
 End-to-end wall time includes single-threaded host preproc (patch-embed + projector, ~1.5 s one-time);
 the NPU compute itself is the table above.
 
-## Notes
-- Arch: **v79 only** — context binaries are dsp-arch-pinned. Other arches must be re-exported.
-- No custom op-package needed — all graphs are pure-native HTP (HVX/HMX).
-- **Precision**: vision fp16, prefill fp16, decode **W4A16**, lm-head **W8A16**. (Prefill/vision can be
-  further quantized to shrink the footprint; this bundle ships the validated balance.)
-- **HTP gotcha baked in**: all graph I/O is 2D `[seq,dim]` — HTP mis-lays-out 3D `[1,seq,dim]` tensors.
-  The Conv2d patch-embed and pixel-shuffle are host-side for the same reason.
-- Source model: [`OpenGVLab/InternVL3_5-1B`](https://huggingface.co/OpenGVLab/InternVL3_5-1B)
-  (InternViT-300M + Qwen3-0.6B), exported and compiled with QAIRT 2.45 for
-  `qualcomm-snapdragon-8-elite-for-galaxy`.
+## v75 (SM8650 / soc_model 57)
+
+Device-validated on Galaxy S24 (Hexagon v75): all four context binaries load; image→caption runs end-to-end.
+Vision **206 ms**, prefill TTFT **139 ms**, decode **~23 ms/tok** (QAIRT 2.47, soc 57).
+
+Same graph layout as `v79/` (`ivl_enc2`, `ivl_pf_512`, `ivl_dec_w4`, `ivl_lmh_q`). Vision + prefill are
+**fp16**; lm-head is **W8 weight-only**. Decode graph name is `ivl_dec_w4` but weights are **W8
+weight-only** (per-row int8 via `dump_wqo_params`, not true W4 like `v79/`) — same compile workaround used
+for other v75 LLM bundles on Apple Silicon hosts where `qairt-quantizer` SIGILLs under Docker.
+
+### Files (`v75/`)
+| file | what | size |
+|------|------|------|
+| `internvl3_5-1b-512.json` | QHexRT manifest (`dsp_arch: v75`) | — |
+| `ivl_enc2.bin` | InternViT-300M vision encoder (**fp16**) | 592 MB |
+| `ivl_pf_512.bin` | Batched LLM prefill Pn=512 (**fp16**) | 855 MB |
+| `ivl_dec_w4.bin` | GQA-native decode MAXCTX=512 (**W8 weight-only**, graph name `ivl_dec_w4`) | 424 MB |
+| `ivl_lmh_q.bin` | Untied lm-head (**W8 weight-only**) | 151 MB |
+| `ivl_embed_f16.bin` | Token embedding table f16 | 297 MB |
+| `ivl_tokenizer.json` | Qwen2 tokenizer — **separate filename** so it does not collide with other QHexRT bundles on device | 11 MB |
+| `vlm/` | Host patch-embed + pixel-shuffle projector + prompt template | 27 MB |
+
+Total ≈ **2.3 GB**.
+
+```bash
+adb push internvl3_5_1b_HNPU/v75 /data/local/tmp/wq/internvl
+adb push my_photo.jpg /data/local/tmp/wq/internvl/
+adb shell "cd /data/local/tmp/wq && export ADSP_LIBRARY_PATH='/data/local/tmp/wq/dsp;/data/local/tmp/wq;/vendor/dsp/cdsp'; \
+  LD_LIBRARY_PATH=. ./qhx_generate internvl/internvl3_5-1b-512.json libQnnHtp.so libQnnSystem.so internvl \
+  60 'Describe this image in detail.' internvl/my_photo.jpg"
+```
 
 ## v81 (SM8850 / soc_model 87)
 
-Device-validated on SM8850: image->caption tracks the image — e.g. an orange dahlia ->
+Device-validated on SM8850: image→caption tracks the image — e.g. an orange dahlia ->
 *"The image features a close-up of a single, large, orange flower with a textured, layered appearance. The
 flower has a circular shape with numerous petals radiating from a central point..."*. Vision 147 ms, prefill
 TTFT 115 ms, decode 18.4 ms/tok. The v81 recipe was **completed** by reconstructing the two graphs the
@@ -91,3 +121,12 @@ lm-head graph (`ivl_lmh`) — both gated vs the HF gold first token. All graphs
 `internvl3_5-1b.json` · `ivl_enc_f16.bin` (InternViT-300M vision) · `ivl_pf_f16.bin` (batched prefill) ·
 `ivl_dec_f16.bin` (AR=1 decode) · `ivl_lmh_f16.bin` (lm-head) · `ivl_embed_f16.bin` · `tokenizer.json` ·
 `vlm/` (host patch/pos-embed + pixel-shuffle MLP projector weights + prompt template).
+
+## Notes
+- Context binaries are **dsp-arch-pinned** — use the sibling `<arch>/` dir that matches your device.
+- No custom op-package needed — all graphs are pure-native HTP (HVX/HMX).
+- **Precision (v79)**: vision fp16, prefill fp16, decode **W4A16**, lm-head **W8A16**.
+- **HTP gotcha baked in**: all graph I/O is 2D `[seq,dim]` — HTP mis-lays-out 3D `[1,seq,dim]` tensors.
+  The Conv2d patch-embed and pixel-shuffle are host-side for the same reason.
+- Source model: [`OpenGVLab/InternVL3_5-1B`](https://huggingface.co/OpenGVLab/InternVL3_5-1B)
+  (InternViT-300M + Qwen3-0.6B).