[MetaxGPU] Support FastDeploy on metax gpu (#3241)

* [MetaxGPU] Support FastDeploy on metax gpu

* Update metax_worker.py

1. change worker log;
2. remove custom allreduce, adapt it later;
3. remove cuda graph;

* Update __init__.py

1. remove metax's key work comment

* Update __init__.py

1. remove metax's key word comment;
2. add fused_moe_kernel_paddle import

---------

Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
Kane2011
2025-08-13 11:11:54 +08:00
committed by GitHub
parent ed6bff215a
commit b4fef2cf29
29 changed files with 3224 additions and 11 deletions

View File

@@ -49,6 +49,12 @@ def get_moe_method():
from fastdeploy.model_executor.layers.backends import GCUFusedMoeMethod
return GCUFusedMoeMethod(None)
elif current_platform.is_maca():
from fastdeploy.model_executor.layers.backends import (
MetaxTritonWeightOnlyMoEMethod,
)
return MetaxTritonWeightOnlyMoEMethod(None)
raise NotImplementedError