From 0899aa1b97f022241cf5beec0b9d4edeed63b32b Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Sat, 16 May 2026 22:59:03 -0400 Subject: [PATCH] Update rtx6000-vllm.yaml --- infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml index b91d403..d95af39 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -51,7 +51,7 @@ spec: - --enable-prefix-caching - --tool-call-parser=qwen3_xml - --reasoning-parser=qwen3 - - --speculative-config {"method": "mtp", "num_speculative_tokens": 2} + - --speculative-config "{"method": "mtp", "num_speculative_tokens": 2}" ports: - containerPort: 8000