更新 computility-run.yaml

优化启动参数：max-model-len→256K, max-num-seqs→8, batched-tokens→16384, 加prefix-caching和dtype

computility-run.yaml

@@ -1,34 +1,36 @@
 concurrency: 1
 command:
-    - python3
-    - -m
-    - vllm.entrypoints.openai.api_server
-    - --model
-    - /model
-    - --served-model-name
-    - llm
-    - --max-model-len
-    - '100000'
-    - --gpu-memory-utilization
-    - '0.9'
-    - --trust-remote-code
-    - -tp
-    - '4'
-    - --max-num-seqs
-    - '1'
-    - --disable-log-requests
-    - --disable-frontend-multiprocessing
-    - --max-num-batched-tokens
-    - '8192'
-    - --enable-chunked-prefill
-    - --max-seq-len-to-capture
-    - '32768'
-    - --enable-auto-tool-choice
-    - --tool-call-parser
-    - qwen3_coder
-    - --reasoning-parser
-    - qwen3
-    - --enable-prefix-caching
+  - python3
+  - -m
+  - vllm.entrypoints.openai.api_server
+  - --model
+  - /model
+  - --served-model-name
+  - llm
+  - --max-model-len
+  - '256000'
+  - --gpu-memory-utilization
+  - '0.95'
+  - --trust-remote-code
+  - -tp
+  - '4'
+  - --max-num-seqs
+  - '8'
+  - --disable-log-requests
+  - --disable-frontend-multiprocessing
+  - --max-num-batched-tokens
+  - '16384'
+  - --enable-chunked-prefill
+  - --max-seq-len-to-capture
+  - '32768'
+  - --enable-auto-tool-choice
+  - --tool-call-parser
+  - qwen3_coder
+  - --reasoning-parser
+  - qwen3
+  - --enable-prefix-caching
+  - --dtype
+  - half
 env:
-    - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
-      value: 3600
+  - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
+    value: 3600