diff --git a/computility-run.yaml b/computility-run.yaml index e5da63a7..0be4999a 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -8,14 +8,16 @@ command: - --served-model-name - llm - --max-model-len - - '100000' + - '256000' - --gpu-memory-utilization - - '0.90' + - '0.95' - --trust-remote-code - -tp - '4' - --max-num-seqs - '2' + - --max-num-batched-tokens + - '4096' - --disable-log-requests - --disable-frontend-multiprocessing - --enforce-eager @@ -25,6 +27,7 @@ command: - --reasoning-parser - qwen3 - --enable-prefix-caching + - --enable-chunked-prefill - --dtype - half env: