Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
515 Open 14,889 Closed
515 Open 14,889 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

[ARM CPU] hgemm optimized for gqa
#23107 opened Dec 14, 2024 by fajin-corp • Draft
Implements Slice Operator for WebGPU Native
#23106 opened Dec 13, 2024 by prathikr Loading…
Fix Pybind memory leak
#23105 opened Dec 13, 2024 by yuslepukhin Loading…
@snnn
[webgpu] Optimize matmulnbits with M > 1 ep:WebGPU ort-web webgpu provider
#23102 opened Dec 13, 2024 by qjia7 Loading…
14
[WebNN] Fixes MLTensor caching across different contexts
#23100 opened Dec 13, 2024 by egalli Loading…
1
Fix a deadlock bug in EigenNonBlockingThreadPool.h
#23098 opened Dec 13, 2024 by snnn Loading…
6
[js/webgpu] Optimize matmulnbits with M > 1
#23092 opened Dec 12, 2024 by qjia7 Loading…
2
[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…
3
[CANN]: Update the doc of CANN EP
#23087 opened Dec 12, 2024 by bachelor-dou Loading…
3
Add experimental headers to public API
#23078 opened Dec 11, 2024 by yihonglyu Loading…
[WebNN] Add limit to QDQ ops
#23076 opened Dec 11, 2024 by Honry Loading…
1
[WebNN EP] Automatically move input CPU tensors to ml-tensor
#23073 opened Dec 11, 2024 by egalli Loading…
16
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…
41
Update python version metadata (remove 3.7, 3.8, 3.9; add 3.13).
#23067 opened Dec 10, 2024 by tianleiwu Loading…
1
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
Make static KV cache work. ep:WebGPU ort-web webgpu provider
#23061 opened Dec 10, 2024 by satyajandhyala Loading…
7
[VitisAI] Add profiler interface for vitisai
#23032 opened Dec 6, 2024 by tianfang-fafafa Loading…
10
Implement DepthToSpace uint8_t and Enable DropQDQNodesRules
#23029 opened Dec 5, 2024 by yihonglyu Loading…
[TensorRT EP] New CIs to test TRT+minimal CUDA build
#23028 opened Dec 5, 2024 by yf711 Loading…
3
Upgrade react-native to 0.70
#23015 opened Dec 5, 2024 by jchen351 Loading…
3
[TensorRT EP] support TensorRT 10.7-GA
#23011 opened Dec 4, 2024 by yf711 Loading…
[DML] Don't save resources to be released later when the GPU is already done with them.
#22995 opened Dec 3, 2024 by BTurkelson Loading…
1
ProTip! Updated in the last three days: updated:>2024-12-11.