-
Notifications
You must be signed in to change notification settings - Fork 3.5k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[webgpu] Fused SplitPackedQKV with FusedQKRotaryEmbedding
ep:WebGPU
ort-web webgpu provider
#26447
opened Oct 30, 2025 by
xiaofeihan1
Loading…
webgpu: optimize Gemm and MatMul using subgroup feature
ep:WebGPU
ort-web webgpu provider
#26433
opened Oct 29, 2025 by
xhcao
Loading…
[webgpu] revise implementation of buffer split support
ep:WebGPU
ort-web webgpu provider
#26429
opened Oct 29, 2025 by
fs-eire
Loading…
webgpu / nbitmm support for bias and weight_index
ep:WebGPU
ort-web webgpu provider
#26392
opened Oct 23, 2025 by
guschmue
Loading…
Add more tests to GatherBlockQuantized operator
ep:WebGPU
ort-web webgpu provider
#25639
opened Aug 2, 2025 by
xiaomsft
Loading…
[WebGPU] Subgroup matrix for GEMM
ep:WebGPU
ort-web webgpu provider
#25416
opened Jul 16, 2025 by
xiaofeihan1
Loading…
Add dynamic bucket cache mode to improve peak and avg gpu buffer memory usage
ep:WebGPU
ort-web webgpu provider
#25120
opened Jun 20, 2025 by
feich-ms
Loading…
[WIP] more fusion in llm - propose GemmQuickGelu
ep:WebGPU
ort-web webgpu provider
#24105
opened Mar 19, 2025 by
guschmue
Loading…
[js/webgpu] Enable graph capture with memcpy and fix duplicated dispatch
ep:WebGPU
ort-web webgpu provider
#22883
opened Nov 19, 2024 by
axinging
Loading…
ProTip!
Adding no:label will show everything without a label.