diff --git a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml index ccf1603..0c4989e 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -24,7 +24,7 @@ spec: effect: "NoSchedule" containers: - name: vllm-brain - image: vllm/vllm-openai:0.20.1 + image: vllm/vllm-openai:latest-cu129-ubuntu2404 command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] env: - name: HF_TOKEN