diff --git a/computility-run.yaml b/computility-run.yaml index d283b113..4522b6e1 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -10,16 +10,16 @@ command: - --max-model-len - '100000' - --gpu-memory-utilization - - '0.95' + - '0.9' - --trust-remote-code - -tp - '4' - --max-num-seqs - - '256' + - '8' - --disable-log-requests - --disable-frontend-multiprocessing - --max-num-batched-tokens - - '32768' + - '8192' - --enable-chunked-prefill - --max-seq-len-to-capture - '32768'