RTX4090笔电操作记录

2025-10-15 10:24:57 +08:00 · 2025-10-15 10:24:57 +08:00 · 8afcf49879
commit 8afcf49879
parent fbc162cbec
1 changed files with 1 additions and 0 deletions
--- a/20251014.md
+++ b/20251014.md
@ -53,6 +53,7 @@ vllm serve \
    --host 0.0.0.0 \
    --port 18778 \
    --model /home/ss/vllm-py12/qwen3-06b \
+    --served-model-name qwen3-06b \
    --tensor-parallel-size 1 \
    --dtype auto \
    --gpu-memory-utilization 0.9 \