v2: conservative max-num-seqs=8 + batched-tokens=16384, revert dtype/256K (v1 OOM crash)

2026-10-01 23:29:16 +08:00
parent a56835199e
commit 0916ad6b91
1 changed files with 31 additions and 33 deletions
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -1,36 +1,34 @@
 concurrency: 1
 command:
-  - 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
+    - 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
+    - '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
 env:
-  - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
-    value: 3600
+    - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
+      value: 3600