This commit is contained in:
parent
59994bb576
commit
d0ce165427
2
vllm.sh
2
vllm.sh
|
@ -1 +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
|
||||
python -m vllm.entrypoints.openai.api_server --model /model/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
|
||||
|
|
Loading…
Reference in New Issue