diff --git a/Dockerfile b/Dockerfile index 84bed2a9..f0d73a7f 100644 --- a/Dockerfile +++ b/Dockerfile @@ -8,11 +8,25 @@ COPY ./qwen3_6_scripts /workspace/qwen3_6_scripts COPY ./computility-run.yaml /workspace/computility-run.yaml COPY ./ex_engine /workspace/ex_engine -# Build & deploy: all steps tolerant (;true ensures non-zero won't kill Docker build) -RUN cd /workspace/ex_engine && bash build.sh --corex 2>&1 || true ; \ - python3 /workspace/ex_engine/precompile_moe_topk.py 2>&1 || true ; \ - python3 /workspace/ex_engine/precompile_moe_kernels.py 2>&1 || true ; \ - cd /workspace/qwen3_6_scripts && bash ./patch_ops.sh 2>&1 || true ; \ - python3 /workspace/qwen3_6_scripts/precompile_gdn.py \ - /workspace/qwen3_6_scripts/flash_qla_sm70 2>&1 || true ; \ - echo "[Dockerfile] All build steps completed" +# 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) +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: $?"