[fix] baseline5 yaml not found template

computility-run.yaml

@@ -1,37 +1,28 @@
 concurrency: 1
 command:
-    - python3
+    - bash
-    - -m
+    - -c
-    - vllm.entrypoints.openai.api_server
+    - >-
-    - --model
+        python3 /workspace/qwen3_6_scripts/patch_chat_template.py /model 2>&1 || echo '[runtime] chat template patch failed';
-    - /model
+        exec python3 -m vllm.entrypoints.openai.api_server
-    - --served-model-name
+        --model /model
-    - llm
+        --served-model-name llm
-    - --max-model-len
+        --max-model-len 131072
-    - '131072'
+        --gpu-memory-utilization 0.92
-    - --gpu-memory-utilization
+        --trust-remote-code
-    - '0.92'
+        -tp 4
-    - --trust-remote-code
+        --max-num-seqs 2
-    - -tp
+        --disable-log-requests
-    - '4'
+        --disable-frontend-multiprocessing
-    - --max-num-seqs
+        --max-num-batched-tokens 4096
-    - '2'
+        --enable-chunked-prefill
-    - --disable-log-requests
+        --max-seq-len-to-capture 32768
-    - --disable-frontend-multiprocessing
+        --enable-auto-tool-choice
-    - --max-num-batched-tokens
+        --tool-call-parser qwen3_coder
-    - '4096'
+        --reasoning-parser qwen3
-    - --enable-chunked-prefill
+        --enable-prefix-caching
-    - --max-seq-len-to-capture
+        --enforce-eager
-    - '32768'
+        --dtype half
-    - --enable-auto-tool-choice
-    - --tool-call-parser
-    - qwen3_coder
-    - --reasoning-parser
-    - qwen3
-    - --enable-prefix-caching
-    - --enforce-eager
-    - --dtype
-    - half
 env:
     - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
       value: '3600'