fix token length problem

2026-04-21 03:39:54 +00:00 · 2026-04-21 03:39:54 +00:00 · 1d7bb9cba3
commit 1d7bb9cba3
parent fd3e3d8f45
1 changed files with 2 additions and 1 deletions
--- a/apps/base/customer1/openclaw/vllm-l4.yaml
+++ b/apps/base/customer1/openclaw/vllm-l4.yaml
@ -38,7 +38,8 @@ spec:
            - --port=8000
            - --tensor-parallel-size=1
            - --gpu-memory-utilization=0.95
-            - --max-model-len=16384
+            - --max-model-len=24576
+            - --kv-cache-dtype=fp8 
            - --max-num-batched-tokens=2048
            - --max-num-seqs=128
            - --enable-chunked-prefill