From a56835199ebece379424e0b6b5acdf15ad08e450 Mon Sep 17 00:00:00 2001 From: wanglin <2281216234@qq.com> Date: Thu, 24 Sep 2026 07:57:33 +0800 Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20computility-run.yaml?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 | 64 +++++++++++++++++++++++--------------------- 1 file changed, 33 insertions(+), 31 deletions(-) diff --git a/computility-run.yaml b/computility-run.yaml index 6447abd..e301cdd 100644 --- a/computility-run.yaml +++ b/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 \ No newline at end of file