不支持sglang

#18

by zhangdahaodaddy - opened Sep 12

Sep 12

docker run --name vllm-minicpm3-4b --runtime nvidia --gpus '"device=0,1"' -v /home/jszc/vllm:/root/.cache/modelscope -p 11436:8080 --ipc=host my_vllm_updated:latest --model /root/.cache/modelscope/MiniCPM3-4B --port=8080 --served-model-name llama3.1-8b --gpu-memory-utilization 0.95 --max_num_seqs 1024 --max_num_batched_tokens 8192 -tp 2 --enable-chunked-prefill true --enable-prefix-caching --trust-remote-code

FrankC0st1e

OpenBMB org Sep 12

The latest main branch of sglang has merged our commit about minicpm3. You can wait for the next release of sglang or build from source to get a version that supports minicpm3.

neoz changed discussion status to closed Sep 18

zhangdahaodaddy

Sep 19

The latest main branch of sglang has merged our commit about minicpm3. You can wait for the next release of sglang or build from source to get a version that supports minicpm3.

Thank you for your reply

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment