diff --git a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml index abaab2b..38b4018 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -52,7 +52,7 @@ spec: - --tool-call-parser=qwen3_xml - --reasoning-parser=qwen3 - --speculative-config - - --'{"method": "mtp", "num_speculative_tokens": 2}' + - '{"method": "mtp", "num_speculative_tokens": 2}' ports: - containerPort: 8000