Update rtx6000-vllm.yaml

2026-05-04 22:01:15 -04:00 · 2026-05-04 22:01:15 -04:00 · 882be08f17
commit 882be08f17
parent 16c8ebc41b
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
@ -41,7 +41,7 @@ spec:
            - --gpu-memory-utilization=0.98
            - --max-model-len=262144
            - --enable-auto-tool-choice 
-            - --disable-chunked-prefill
+            
            - --max-num-batched-tokens=65536
            - --max-num-seqs=8
            - --trust-remote-code