This commit is contained in:
sirius0xdev 2026-04-21 03:55:18 +00:00
parent 1d7bb9cba3
commit 10d2ff67c1

View file

@ -38,7 +38,7 @@ spec:
- --port=8000 - --port=8000
- --tensor-parallel-size=1 - --tensor-parallel-size=1
- --gpu-memory-utilization=0.95 - --gpu-memory-utilization=0.95
- --max-model-len=24576 - --max-model-len=32768
- --kv-cache-dtype=fp8 - --kv-cache-dtype=fp8
- --max-num-batched-tokens=2048 - --max-num-batched-tokens=2048
- --max-num-seqs=128 - --max-num-seqs=128