deploy qwen3.5 and nemotron

This commit is contained in:
2026-03-17 21:05:19 +08:00
parent 825c64c4dd
commit b48d522bb3
4 changed files with 4911 additions and 1 deletions

13
vllm-qwen3.5-27b.sh Normal file
View File

@@ -0,0 +1,13 @@
#! /bin/bash
export CUDA_VISIBLE_DEVICES="4,5"
#export PYTHONWARNINGS="ignore::UserWarning:vllm.model_executor.layers.fla"
MODEL="/home/kongcunliang/workspace/pretrained-models/Qwen/Qwen3.5-27B-FP8"
vllm serve $MODEL \
--served-model-name "Qwen3.5-27B" \
--port 8000 \
--tensor-parallel-size 2 \
--max-model-len 262144 \
--reasoning-parser qwen3
# --speculative-config '{"method":"mtp","num_speculative_tokens":1}'