frank-primary: digest-pin FreeToken base image, symlink libhiprtc dev name

- FROM pinned to sha256:a223aee1... (the pulled rocm/pytorch rocm7.14
  pytorch 2.11.0 manifest); a re-pushed tag cannot change the stack.
- The pip-ROCm torch ships libhiprtc.so.7 only; the PR's _cpu_moe links
  -lhiprtc and ld needs the unversioned symlink in the already-linked
  _rocm_sdk_core/lib (first build died: cannot find -lhiprtc).
This commit is contained in:
Frank
2026-10-05 19:11:15 -07:00
parent 1f6bdac759
commit 4a02dc0980
@@ -29,10 +29,19 @@
# / 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
#
# Base is digest-pinned (2026-10-05): sha256:a223aee1… is the manifest this
# build was qualified against; a re-pushed tag cannot change the stack.
FROM rocm/pytorch@sha256:a223aee17aef5d21c3b9f63436dd19d27d1c665ec8b2f40011c9546cabae2a80
# Pin the PR head, not the branch: a future push to rocm714_torch214 would
# otherwise silently change the deployed engine.
# The pip-ROCm torch in this image ships libhiprtc as the VERSIONED
# libhiprtc.so.7 only; the PR's `_cpu_moe` extension links `-lhiprtc`, and
# ld looks for the unversioned dev symlink in the ALREADY-LINKED
# _rocm_sdk_core/lib dir. Create it there (first build failure 2026-10-05:
# `ld: cannot find -lhiprtc`).
RUN ln -s libhiprtc.so.7 /opt/venv/lib/python3.12/site-packages/_rocm_sdk_core/lib/libhiprtc.so
RUN git clone https://github.com/FlashML-org/FreeToken.git /opt/FreeToken \
&& cd /opt/FreeToken \
&& git fetch origin pull/587/head \