Skip to content

Quickstart

Currently the recommanded way to start vLLM-MetaX is via docker.

You could get the docker image at MetaX develop community.

Note

After v0.11.2, vllm-metax moved its _C and _moe_C kernel into a separate package named mcoplib.

mcoplib is open-sourced at MetaX-mcoplib and would maintain its own release cycle. Please always install the corresponding version of mcoplib when using vLLM-MetaX.

Though the csrc folder is still kept in this repo for development convenience, and there is no guarantee that the code is always in sync with mcoplib. Not only the performance but also the correctness may differ from mcoplib.

If you want build the latest vllm-metax, please refer to installation to build from source.

Please always use mcoplib for production usage.

Releases

Belows is version mapping to released plugin and mcoplib with maca:

plugin version maca version mcoplib version docker distribution tag
v0.8.5 maca2.33.1.13 N/A vllm:maca.ai2.33.1.13-torch2.6-py310-ubuntu22.04-amd64
v0.9.1 maca3.0.0.5 N/A vllm:maca.ai3.0.0.5-torch2.6-py310-ubuntu22.04-amd64
v0.10.2 maca3.2.1.7 N/A vllm-metax:0.10.2-maca.ai3.2.1.7-torch2.6-py310-ubuntu22.04-amd64
v0.11.0 maca3.3.0.15 0.1.1 vllm-metax:0.11.0-maca.ai3.3.0.11-torch2.6-py312-ubuntu22.04-amd64
v0.11.2 maca3.3.0.15 0.2.0 vllm-metax:0.11.2-maca.ai3.3.0.103-torch2.8-py312-ubuntu22.04-amd64
v0.12.0 maca3.3.0.15 0.3.0 vllm-metax:0.12.0-maca.ai3.3.0.204-torch2.8-py312-ubuntu22.04-amd64
v0.13.0 maca3.3.0.15 0.3.1 vllm-metax:0.13.0-maca.ai3.3.0.303-torch2.8-py312-ubuntu22.04-amd64
master maca3.3.0.15 >=0.3.0 not released

Usage Warning

vLLM-MetaX is out of box via these docker images.

All the vllm tests are based on the related maca version. Using incorresponding version of maca for vllm may cause unexpected bugs or errors. This is not garanteed.