[fix] t2_n_2 max_num_seqs; t13

computility-run.yaml

@@ -1,28 +1,37 @@
 concurrency: 1
 command:
-    - bash
-    - -c
-    - >-
-        python3 /workspace/qwen3_6_scripts/patch_chat_template.py /model 2>&1 || echo '[runtime] chat template patch failed';
-        exec python3 -m vllm.entrypoints.openai.api_server
-        --model /model
-        --served-model-name llm
-        --max-model-len 131072
-        --gpu-memory-utilization 0.92
-        --trust-remote-code
-        -tp 4
-        --max-num-seqs 2
-        --disable-log-requests
-        --disable-frontend-multiprocessing
-        --max-num-batched-tokens 4096
-        --enable-chunked-prefill
-        --max-seq-len-to-capture 32768
-        --enable-auto-tool-choice
-        --tool-call-parser qwen3_coder
-        --reasoning-parser qwen3
-        --enable-prefix-caching
-        --enforce-eager
-        --dtype half
+    - python3
+    - -m
+    - vllm.entrypoints.openai.api_server
+    - --model
+    - /model
+    - --served-model-name
+    - llm
+    - --max-model-len
+    - '131072'
+    - --gpu-memory-utilization
+    - '0.92'
+    - --trust-remote-code
+    - -tp
+    - '4'
+    - --max-num-seqs
+    - '2'
+    - --disable-log-requests
+    - --disable-frontend-multiprocessing
+    - --max-num-batched-tokens
+    - '4096'
+    - --enable-chunked-prefill
+    - --max-seq-len-to-capture
+    - '32768'
+    - --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'
@@ -40,4 +49,7 @@ env:
     - name: BI100_GDN_CACHE_POLICY
       value: admission64
     - name: BI100_GDN_RESTORE_MODE
-      value: hybrid64
+      value: hybrid64
+    # --- Image fetch timeout (container network) ---
+    - name: VLLM_IMAGE_FETCH_TIMEOUT
+      value: '10'