diff --git a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml index 0d058d6..fd254c3 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -41,7 +41,7 @@ spec: - --gpu-memory-utilization=0.98 - --max-model-len=262144 - --enable-auto-tool-choice - - --disable-chunked-prefill + - --max-num-batched-tokens=65536 - --max-num-seqs=8 - --trust-remote-code