Pin ROCmFPX runner and add build instructions

README.md

@@ -41,7 +41,7 @@ The goal is simple: keep Step 3.7 Flash useful at 256K context, keep the quality
 
 Use this if you want the Step 3.7 behavior profile, MTP support, and a much smaller local footprint than the stock GGUF Q3_K_L or ROCmFP4 STRIX_LEAN builds.
 
-> Runtime note: these GGUFs use ROCmFPX tensor types. They are intended for the Chadrock / ROCmFPX llama.cpp runner family, not stock upstream llama.cpp.
+> **Required runtime:** these GGUFs do **not** run on stock upstream llama.cpp. They use ROCmFPX tensor types such as `q3_0_rocmfpx` plus Chadrock/ROCmFPX serving support for Step MTP. Build the pinned Ciru ROCmFPX runner below before trying to load the model.
 
 ## Why This One
 
@@ -161,6 +161,49 @@ Download it from the Files tab or directly from:
 https://huggingface.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus/resolve/main/step37-native-tool-response-template.jinja
 ```
 
+## Required ROCmFPX Runner
+
+This model is tied to the Charlie/Ciru ROCmFPX llama.cpp runner family. A stock `llama-server` will not understand the ROCmFPX tensor types in these shards and will not reproduce the MTP serving behavior used for the benchmark rows.
+
+Use the pinned Ciru runner:
+
+```text
+repo: https://github.com/ciru-ai/ROCmFPX
+current recommended pin: 221402af8574faf652b101b6afe225a3f329561f
+branch at time of pin: main
+upstream lineage: charlie12345/ROCmFPX
+```
+
+The earlier Chadrock v2 speed-runner tag remains useful for historical comparison:
+
+```text
+tag: chadrockv2-runner-20260622
+commit: 7aa484a2f0a504dc612a3d74a068024f3e6d6353
+```
+
+The Q3 QualityPlus Step 3.7 rows on this card were validated with the Chadrock/ROCmFPX runner path on AMD Ryzen AI Max+ 395 / Strix Halo. For fresh installs, use the current Ciru pin above unless you are reproducing an older benchmark exactly.
+
+Build the runner:
+
+```bash
+git clone https://github.com/ciru-ai/ROCmFPX.git
+cd ROCmFPX
+git checkout 221402af8574faf652b101b6afe225a3f329561f
+
+env JOBS="$(nproc)" \
+  CMAKE_HIP_ARCHITECTURES=gfx1151 \
+  ROCMFPX_DECODE_TUNE=stable \
+  scripts/build-strix-rocmfp4-mtp.sh llama-server llama-bench
+```
+
+The server binary should be:
+
+```text
+./build-strix-rocmfp4/bin/llama-server
+```
+
+If the model load fails with an unknown GGUF tensor type, you are using the wrong runner.
+
 ## Recommended Serving Profile
 
 The locally tested long-context profile:
@@ -186,7 +229,7 @@ chat template: Step native tool_response template with protocol-boundary escapin
 Example shape:
 
 ```bash
-/path/to/ROCmFPX/build/bin/llama-server \
+./build-strix-rocmfp4/bin/llama-server \
   -m Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00001-of-00009.gguf \
   --alias step-3.7-flash-rocmfpx-q3-qualityplus \
   --host 127.0.0.1 \
@@ -235,6 +278,8 @@ That matters for real agents because Step 3.7 can otherwise confuse tool output
 
 ## Build Notes
 
+These are model-build notes, not runner-build instructions. Build the pinned ROCmFPX runner in the section above before serving the GGUFs.
+
 The QualityPlus policy used here:
 
 - huge `ffn_*_exps` tensors: `q3_0_rocmfpx`
@@ -250,10 +295,11 @@ Converter-reported size: `83726.08 MiB / 3.57 BPW`, 9 shards.
 - Base model: [`stepfun-ai/Step-3.7-Flash`](https://huggingface.co/stepfun-ai/Step-3.7-Flash)
 - MTP draft GGUF source: [`notSnix/Step-3.7-Flash-MTP-Draft-GGUF`](https://huggingface.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF)
 - ROCmFPX creator: Charlie, `charlie12345` / `@italianclownz`, [`charlie12345/ROCmFPX`](https://github.com/charlie12345/ROCmFPX)
+- Pinned public runner fork and build recipe: [`ciru-ai/ROCmFPX`](https://github.com/ciru-ai/ROCmFPX), current recommended pin `221402af8574faf652b101b6afe225a3f329561f`
 - Quantization, the ROCmFPX Step 3.7 Q3 QualityPlus recipe, Strix Halo profile, and local benchmark work: Crown / Ciru
 
 ## Caveats
 
-- This is a custom ROCmFPX GGUF release. Use a compatible ROCmFPX/Chadrock llama.cpp runner.
+- This is a custom ROCmFPX GGUF release. It requires the compatible ROCmFPX/Chadrock llama.cpp runner; stock llama.cpp is not expected to load it.
 - Quality numbers are local Strix Halo measurements and depend on runtime, chat template, KV type, and MTP settings.
 - The model is strong but not perfect at autonomous email/message side effects; it can be cautious and ask for subject/body/recipient details instead of sending with inferred defaults.