Update rtx6000-vllm.yaml

2026-05-04 15:11:43 -04:00 · 2026-05-04 15:11:43 -04:00 · 73f82dc57c
commit 73f82dc57c
parent 089ba22373
1 changed files with 1 additions and 1 deletions
--- 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
-            - --max-model-len=131072
+            - --max-model-len=262144
            - --enable-auto-tool-choice 
            - --enable-chunked-prefill
            - --max-num-batched-tokens=4096