From 9a7904c219b3e318aeed26cb436d0a9c549edf10 Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Sat, 2 May 2026 08:36:04 -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 7f58b97..1943577 100644 --- a/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml +++ b/infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml @@ -39,7 +39,7 @@ spec: - --tensor-parallel-size=1 - --tokenizer-mode=hf - --gpu-memory-utilization=0.95 - - --kv-cache-dtype=fp8_e5m2 + - --kv-cache-dtype=fp8 - --max-model-len=256389 - --enable-auto-tool-choice - --enable-chunked-prefill