From 5bf0601e8d0c8adf7b86af99c8c6dcae81e3cf00 Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Sun, 24 May 2026 15:58:35 -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 ec44fc3..69dc5f2 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -42,7 +42,7 @@ spec: - --enable-auto-tool-choice - --kv-cache-dtype=auto - --max-num-batched-tokens=16384 - - --max-num-seqs=4 + - --max-num-seqs=12 - --block-size=32 - --language-model-only - --enable-chunked-prefill