whx a58ff9e92f [Cherry-pick] Port MoE multi-stream fix to v0.11.0-dev (#3753) ...

This PR moves the communication operation of shared experts out of extra
stream because I found that this might cause rtMemcpy related errors
when running shared experts multistream with aclgraph.

Furthermore, I utilize a global variable as extra stream object to avoid
allocating streams for each layer in full-graph mode.

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-10-25 15:51:43 +08:00

..

e2e

[Cherry-pick] Port MoE multi-stream fix to v0.11.0-dev (#3753)

2025-10-25 15:51:43 +08:00

ut

[cherry-pick][Feat] Add mrope fusion op#3708 (#3735)

2025-10-25 11:41:23 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00