Skip to content

Add Expert Parallelism for MoE inference #3158

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
0xDaizz wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

Add Expert Parallelism for MoE inference #3158

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4c7b650
Re-acquire Metal command buffer after mid-primitive GPU sync
0xDaizz Feb 23, 2026
3d68fe6
Add all_to_all collective and MoE dispatch/combine C++ primitives
0xDaizz Feb 23, 2026
9398a15
Add MixtureOfExperts layer with EP dispatch/combine Python bindings
0xDaizz Feb 23, 2026
e7a6604
Add EP MoE tests and distributed integration tests
0xDaizz Feb 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions docs/src/python/distributed.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@ made available.
init
all_sum
all_gather
all_to_all
moe_dispatch_exchange
moe_combine_exchange
send
recv
recv_like
1 change: 1 addition & 0 deletions docs/src/python/nn/layers.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ Layers
MaxPool2d
MaxPool3d
Mish
MixtureOfExperts
MultiHeadAttention
PReLU
QuantizedAllToShardedLinear
Expand Down
Loading