Merge pull request #46 from sirius0xdev/feature/maximize-l4-context

Maximize L4 vLLM context window
2026-04-20 12:29:03 -04:00 · 2026-04-20 12:29:03 -04:00 · 2f163fab36
commit 2f163fab36
parent bca7bdec5e fb951600d7
1 changed files with 2 additions and 2 deletions
--- a/apps/base/customer1/openclaw/vllm-l4.yaml
+++ b/apps/base/customer1/openclaw/vllm-l4.yaml
@ -34,8 +34,8 @@ spec:
            - --host=0.0.0.0
            - --port=8000
            - --tensor-parallel-size=1
-            - --gpu-memory-utilization=0.90
-            - --max-model-len=16384
+            - --gpu-memory-utilization=0.95
+            - --max-model-len=32768
            - --enable-auto-tool-choice 
            - --trust-remote-code
            - --dtype=auto