diff --git a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml index fd254c3..fd5f81b 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -39,7 +39,7 @@ spec: - --tensor-parallel-size=1 - --tokenizer-mode=hf - --gpu-memory-utilization=0.98 - - --max-model-len=262144 + - --max-model-len=auto - --enable-auto-tool-choice - --max-num-batched-tokens=65536