From b3fdb91e13fa4d7d2d9e0fa3e02fa2de0059a53d Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Sat, 23 May 2026 00:47:34 -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 62b75d7..6135e98 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -41,7 +41,7 @@ spec: - --max-model-len=131072 - --enable-auto-tool-choice - --kv-cache-dtype=bfloat16 - - --max-num-batched-tokens=4096 + - --max-num-batched-tokens=16384 - --max-num-seqs=64 - --block-size=32 - --language-model-only