frank-primary: add FreeToken PR587 ROCm serving image recipe

Dockerfile builds the FreeToken engine (FlashML-org/FreeToken PR #587, pinned head 77a7201) inside the PR's own known-good ROCm 7.14 base image (torch 2.11/triton 3.7, gfx1201) on dankserver, rootless podman. Follows docs/install_amd.md exactly: --no-build-isolation --no-deps engine install, curated portable runtime deps, flashlib --no-deps, ninja for the QSA JIT; no flashinfer/sgl_kernel on ROCm (Triton fallback).
2026-10-05 19:00:30 -07:00
parent a6ad9af708
commit 1f6bdac759
1 changed files with 53 additions and 0 deletions
@@ -0,0 +1,53 @@
+# frank-primary-freetoken.Dockerfile — FreeToken (PR #587 ROCm) serving image
+# for the frank-primary endpoint (dankserver :7770, 1x R9700 gfx1201).
+#
+# Built on dankserver with rootless podman (dank user), same storage the
+# service's `podman run` reads:
+#   podman build -t frank-primary-freetoken:pr587-77a7201 \
+#     -f scripts/docker/frank-primary-freetoken.Dockerfile scripts/docker/
+#
+# Base: the PR's own docs/install_amd.md names this exact image as the
+# known-good ROCm 7.14 stack for gfx1201 (torch 2.11.0+rocm7.14, triton-rocm
+# 3.7 — the original pin; FreeToken main+PR587 accepts torch>=2.11,<2.16 and
+# triton>=3.6,<3.9). There is no rocm7.14+torch2.14 image on Docker Hub (the
+# 2.14 images are rocm10.1.0 — an untested pair for this PR), so the PR doc's
+# verbatim recommendation is the deployed stack.
+#
+# FreeToken source: FlashML-org/FreeToken PR #587 at pinned head
+# 77a7201f98f00d93f618c6cf8b81ffe8360e0899 (branch rocm714_torch214, base
+# main 581fdca3). The PR is ROCm-gated end to end; the NVIDIA/CUDA path is
+# byte-identical to main.
+#
+# Build law from docs/install_amd.md:
+#   - `pip install --no-build-isolation --no-deps -e .` — the image's ROCm
+#     torch is preserved and used to compile the C++/HIP extensions.
+#   - NEVER a plain `pip install -e .` on ROCm: the dependency set is
+#     authored for NVIDIA (flashlib pulls numba + nvidia-cutlass-dsl; torch
+#     metadata pulls cuda-bindings) and the resolve can REPLACE the ROCm
+#     torch with a CUDA build.
+#   - Runtime deps installed explicitly, curated by the same doc. flashinfer
+#     / sgl_kernel / nvidia-cutlass-dsl have no ROCm builds and are
+#     intentionally absent — FreeToken gates them off and falls back to its
+#     Triton kernels on ROCm.
+FROM rocm/pytorch:rocm7.14_ubuntu24.04_py3.12_pytorch_release_2.11.0
+
+# Pin the PR head, not the branch: a future push to rocm714_torch214 would
+# otherwise silently change the deployed engine.
+RUN git clone https://github.com/FlashML-org/FreeToken.git /opt/FreeToken \
+ && cd /opt/FreeToken \
+ && git fetch origin pull/587/head \
+ && git checkout 77a7201f98f00d93f618c6cf8b81ffe8360e0899
+
+WORKDIR /opt/FreeToken
+RUN python -m pip install --no-build-isolation --no-deps -e .
+
+# Curated runtime dependencies (docs/install_amd.md). transformers is pinned
+# to the pyproject window (>=5.16,<5.17); the rest are the doc's portable set.
+# torch / torchvision / triton-rocm come from the base image, 1:1 aligned.
+RUN python -m pip install \
+      "transformers>=5.16,<5.17" tokenizers safetensors huggingface_hub \
+      fastapi uvicorn pydantic openai httpx anyio \
+      einops gguf msgpack pyzmq typer rich apache-tvm-ffi \
+      partial-json-parser \
+ && python -m pip install --no-deps flashlib==0.3.0 \
+ && python -m pip install ninja