fix error

This commit is contained in:
sirius0xdev 2026-04-22 06:12:32 +00:00
parent c420d2478c
commit c7f0fc7262

View file

@ -36,6 +36,7 @@ spec:
- --host=0.0.0.0
- --port=8000
- --tensor-parallel-size=1
- --tokenizer-mode=hf
- --gpu-memory-utilization=0.95
- --kv-cache-dtype=fp8
- --max-model-len=49152