Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
514 Open 14,907 Closed
514 Open 14,907 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[WebGPU EP] allows GPUDevice to be released after use
#23144 opened Dec 18, 2024 by fs-eire Loading…
[webgpu] support Pad operator
#23141 opened Dec 18, 2024 by xhcao Loading…
1
[webgpu] Always use tile matmulnbits for block_size = 32
#23140 opened Dec 18, 2024 by qjia7 Loading…
1
[webgpu] fix compiling error
#23139 opened Dec 18, 2024 by xhcao Loading…
11
gather elements webgpu implementation ep:WebGPU ort-web webgpu provider
#23137 opened Dec 18, 2024 by prathikr Loading…
[WIP] Add QNN EP HTP shared memory allocator
#23136 opened Dec 18, 2024 by edgchen1 • Draft
3
Enable pointer-generator T5 models in BeamSearch
#23134 opened Dec 17, 2024 by amancini-N Loading…
1
16
Revert "[js/webgpu] disable failed tests temporarily (#23127)"
#23130 opened Dec 17, 2024 by fs-eire Loading…
Make MultiHeadAttention op return attention probabilities
#23125 opened Dec 16, 2024 by amancini-N Loading…
1
9
[QNN EP] [DRAFT] Make QNN EP a shared library ep:QNN issues related to QNN exeution provider
#23120 opened Dec 16, 2024 by adrianlizarraga • Draft
[Fix] in Xnnpack EP, the conversion for fused activation param isn't correct
#23115 opened Dec 16, 2024 by mszhanyi Loading…
3
Fix delay load for WebGPU EP and DML EP
#23111 opened Dec 15, 2024 by fs-eire Loading…
1
Enable dlpack by default
#23110 opened Dec 15, 2024 by take-cheeze Loading…
1
Update OpenVINO-ExecutionProvider.md
#23109 opened Dec 14, 2024 by andife Loading…
[ARM CPU] hgemm optimized for gqa
#23107 opened Dec 14, 2024 by fajin-corp • Draft
Implements Slice Operator for WebGPU Native ep:WebGPU ort-web webgpu provider
#23106 opened Dec 13, 2024 by prathikr Loading…
[js/webgpu] Optimize matmulnbits with M > 1 ep:WebGPU ort-web webgpu provider
#23092 opened Dec 12, 2024 by qjia7 Loading…
10
[Bug Fix] Missing CustomOp SchemaRegister when generator EPContext ONNX model
#23091 opened Dec 12, 2024 by mingyueliuh Loading…
1
Implement some missing element wise Add/Sub/Mul/Div/Neg operations for CPU and CUDA EPs
#23090 opened Dec 12, 2024 by Zyrin Loading…
19
Add experimental headers to public API
#23078 opened Dec 11, 2024 by yihonglyu Loading…
[WebNN EP] Automatically move input CPU tensors to ml-tensor ep:WebNN WebNN execution provider
#23073 opened Dec 11, 2024 by egalli Loading…
25
Improves 2d tiled matmulnbits by repeating A, loads N times for each B load ep:WebGPU ort-web webgpu provider
#23071 opened Dec 10, 2024 by sushraja-msft Loading…
8
Implement pre-packed blobs serialization on disk and their memory mapping on load
#23069 opened Dec 10, 2024 by yuslepukhin Loading…
46
Upgrade Java version from react-native/android to Java 17
#23066 opened Dec 10, 2024 by jchen351 Loading…
[CoreML] support coreml model cache
#23065 opened Dec 10, 2024 by wejoncy Loading…
1
24
ProTip! Filter pull requests by the default branch with base:main.