之前新增的Step 5(bridge build)/Step 6(deploy)/Step 7(gdn)结构 在竞赛平台Docker build失败。真机上全部exit 0但竞赛平台环境不同。 回退到26e6cb40已验证能通过的Dockerfile结构: Step 1: build.sh Step 2: precompile_moe_topk Step 3: precompile_moe_kernels Step 4: patch_ops.sh (已包含bridge build + deploy逻辑) Step 5: precompile_gdn 所有增强功能(bridge build/deploy/ix_unified等)通过patch_ops.sh 在Step 4中完成,不需要额外的Dockerfile RUN step。
34 lines
1.5 KiB
Docker
34 lines
1.5 KiB
Docker
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 -p /workspace
|
|
WORKDIR /workspace/
|
|
|
|
# Copy all sources
|
|
COPY ./qwen3_6_scripts /workspace/qwen3_6_scripts
|
|
COPY ./computility-run.yaml /workspace/computility-run.yaml
|
|
COPY ./ex_engine /workspace/ex_engine
|
|
|
|
# Step 1: Build EX Engine .so libraries
|
|
RUN chmod +x /workspace/ex_engine/build.sh && \
|
|
bash /workspace/ex_engine/build.sh --corex 2>&1 | tee /workspace/ex_build.log ; \
|
|
echo "[Dockerfile] ex_engine build exit code: $?"
|
|
|
|
# Step 2: Precompile MoE CUDA kernels
|
|
RUN python3 /workspace/ex_engine/precompile_moe_topk.py 2>&1 | tee -a /workspace/ex_build.log ; \
|
|
echo "[Dockerfile] moe_topk precompile exit code: $?"
|
|
|
|
# Step 3: Precompile vllm v0.5.5 MoE kernels
|
|
RUN python3 /workspace/ex_engine/precompile_moe_kernels.py 2>&1 | tee -a /workspace/ex_build.log ; \
|
|
echo "[Dockerfile] moe_v055 precompile exit code: $?"
|
|
|
|
# Step 4: Deploy patches (serving + engine fixes)
|
|
# patch_ops.sh also builds bridge, deploys .so and Python modules
|
|
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: $?"
|
|
|
|
# Step 5: Precompile GDN kernel (needs vllm in path, so after patch_ops)
|
|
RUN python3 /workspace/qwen3_6_scripts/precompile_gdn.py \
|
|
/workspace/qwen3_6_scripts/flash_qla_sm70 2>&1 | tee -a /workspace/ex_build.log ; \
|
|
echo "[Dockerfile] gdn precompile exit code: $?"
|