vllm

2025-01-09 20:47:38 +08:00 · 2025-01-09 20:47:38 +08:00 · 59994bb576
parent dbf3f8dc87
commit 59994bb576
1 changed files with 1 additions and 0 deletions
--- a/vllm.sh
+++ b/vllm.sh
@ -0,0 +1 @@
+python -m vllm.entrypoints.openai.api_server --model /home/pubw/proj/Qwen2-VL-72B-Instruct-GPTQ-Int4   --served-model-name Qwen2-7B-Instruct --tensor-parallel-size 4 --limit-mm-per-prompt image=2 --gpu-memory-utilization 0.95 --port 12345
				`@ -0,0 +1 @@`
				`python -m vllm.entrypoints.openai.api_server --model /home/pubw/proj/Qwen2-VL-72B-Instruct-GPTQ-Int4 --served-model-name Qwen2-7B-Instruct --tensor-parallel-size 4 --limit-mm-per-prompt image=2 --gpu-memory-utilization 0.95 --port 12345`