fix(build): 回退qwen3_6_scripts+ex_engine到26e6cb40(能得分版本)

唯一改动: computility-run.yaml max_model_len 80000→100000

26e6cb40是Sub520能在竞赛平台docker build成功并得分的版本
之后所有commit都导致docker build失败
根因: 新增的65个文件(vendor_overrides/prebuilt/*.so/wheels等)
可能触发了竞赛平台docker build的某个限制

本次回退:
- qwen3_6_scripts/: 110→45文件(删掉65个新增文件)
- ex_engine/: 恢复到26e6cb40完全一致
- Dockerfile: 恢复5个RUN步骤结构(已验证能build)
- computility-run.yaml: max_model_len=100000(避免replay 400拒绝)

Dockerfile

@@ -3,12 +3,30 @@ FROM git.modelhub.org.cn:9443/enginex-iluvatar/bi100-3.2.3-x86-ubuntu20.04-py3.1
 RUN mkdir -p /workspace
 WORKDIR /workspace/
 
-# Copy all our engine patches + prebuilt .so
+# 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
 
-# Single patch step — NO CUDA compilation during docker build
-# All .so are prebuilt and bundled in qwen3_6_scripts/prebuilt/
+# 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: $?"