webgpu qmoe
67a974e0
Update onnxruntime/contrib_ops/webgpu/moe/swiglu.wgsl.template
6afc761c
Update onnxruntime/contrib_ops/webgpu/moe/zero_tensor.wgsl.template
61dfdbcb
Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
f64e588b
Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
48f93866
Update onnxruntime/contrib_ops/webgpu/moe/hidden_state_gather.wgsl.te…
32ee5bc3
Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
21d8cc93
Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
9152e1fd
guschmue
marked this pull request as ready for review 116 days ago
fix lint errors
9f055eca
qjia7
commented
on 2025-11-10
address review feedback
336cafad
address review feedback
75fc0522
fix chunking of tokens into max_token blocks
55fea842
Merge branch 'main' into gs/webgpu-qmoe
44c621b9
reflect changes in main
9aac0543
qjia7
commented
on 2025-11-11
review feedback
d6fd933a
qjia7
dismissed these changes
on 2025-11-12
qjia7
commented
on 2025-11-12
fix build
114d2280
guschmue
dismissed their stale review
via 114d2280
108 days ago
qjia7
approved these changes
on 2025-11-12
fs-eire
approved these changes
on 2025-11-12
guschmue
merged
59557984
into main 107 days ago
guschmue
deleted the gs/webgpu-qmoe branch 107 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub