diff --git a/computility-run.yaml b/computility-run.yaml index f02fcda2..6c0d5cb1 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -8,21 +8,16 @@ command: - --served-model-name - llm - --max-model-len - - '131072' + - '100000' - --gpu-memory-utilization - '0.90' - --trust-remote-code - -tp - '4' - --max-num-seqs - - '2' + - '1' - --disable-log-requests - --disable-frontend-multiprocessing - - --max-num-batched-tokens - - '8192' - - --enable-chunked-prefill - - --max-seq-len-to-capture - - '32768' - --enforce-eager - --enable-auto-tool-choice - --tool-call-parser