From 6df297086c5e98298d08d2438db636b4fec7ae58 Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Fri, 22 May 2026 13:56:53 -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 5f613cf..186d1d6 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -39,7 +39,7 @@ spec: - --tokenizer-mode=hf - --gpu-memory-utilization=0.90 #- --enforce-eager - - --max-model-len=136876 + - --max-model-len=131072 - --enable-auto-tool-choice - --kv-cache-dtype=bfloat16 - --max-num-batched-tokens=32768