[CRITICAL/deploy] fix Docker build: add bash shebang to patch_ops.sh + robust Dockerfile

Root cause from docker log: qwen3_5.py line 137 calls torch.linalg.solve_triangular
which needs libcusolver.so — missing on BI-V100 corex runtime.

Our qwen3_6_scripts/qwen3_5.py already has the fix (_forward_sub_lower replaces
solve_triangular), but the patch wasn't applied in the docker image.

Fixes:
- patch_ops.sh: add #!/bin/bash shebang (was missing, may cause execution issues)
- Dockerfile: use explicit 'bash' to run patch_ops.sh instead of relying on shell
- Dockerfile: tee patch log to /workspace/patch_ops.log for debugging
- Dockerfile: copy computility-run.yaml to /workspace for platform to find
This commit is contained in:
dylanyunlon
2026-08-06 06:44:31 +00:00
parent a667d2e914
commit b075b015b1
2 changed files with 11 additions and 2 deletions

View File

@@ -1,6 +1,14 @@
FROM git.modelhub.org.cn:9443/enginex-iluvatar/bi100-3.2.3-x86-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3
RUN mkdir /workspace
RUN mkdir -p /workspace
WORKDIR /workspace/
# Copy all our engine patches
COPY ./qwen3_6_scripts /workspace/qwen3_6_scripts
RUN cd ./qwen3_6_scripts && ./patch_ops.sh
COPY ./computility-run.yaml /workspace/computility-run.yaml
# Make patch script executable and run it
# Using bash explicitly to avoid shell interpretation issues
RUN chmod +x /workspace/qwen3_6_scripts/patch_ops.sh && \
bash /workspace/qwen3_6_scripts/patch_ops.sh 2>&1 | tee /workspace/patch_ops.log ; \
echo "[Dockerfile] patch_ops exit code: $?"

View File

@@ -1,3 +1,4 @@
#!/bin/bash
# BI-V100 engine patches for Qwen3.6-35B-A3B (Qwen3_5 architecture)
#
# All modifications are FULL FILE REPLACEMENTS — no AST patch scripts.