[feat] FlashInfer CuteDSL MegaMoE integration (#54049)
Signed-off-by: jdebache <jdebache@nvidia.com>
This commit is contained in:
@@ -49,6 +49,20 @@ if has_flashinfer_nvlink_one_sided():
|
||||
logger = init_logger(__name__)
|
||||
|
||||
|
||||
class PassThroughAll2AllManager(All2AllManagerBase):
|
||||
"""Placeholder for ``all2all_backend="passthrough"``.
|
||||
|
||||
The MoE backend dispatches and combines itself, so there is no all2all to
|
||||
manage.
|
||||
"""
|
||||
|
||||
def get_handle(self, kwargs):
|
||||
raise RuntimeError(
|
||||
"passthrough has no all2all handle: dispatch and combine run "
|
||||
"inside the MoE backend."
|
||||
)
|
||||
|
||||
|
||||
class AgRsAll2AllManager(All2AllManagerBase):
|
||||
"""An implementation of all2all communication based on
|
||||
all-gather (dispatch) and reduce-scatter (combine).
|
||||
|
||||
@@ -255,6 +255,12 @@ class CudaCommunicator(DeviceCommunicatorBase):
|
||||
from .all2all import FlashInferNVLinkOneSidedManager
|
||||
|
||||
self.all2all_manager = FlashInferNVLinkOneSidedManager(self.cpu_group)
|
||||
elif self.all2all_backend == "passthrough":
|
||||
from .all2all import PassThroughAll2AllManager
|
||||
|
||||
self.all2all_manager = PassThroughAll2AllManager(
|
||||
self.cpu_group, tcp_store_group
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unknown all2all backend: {self.all2all_backend}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user