Skip to content

Pull requests: ROCm/AMDMIGraphX

New pull request New
75 Open 957 Closed
75 Open 957 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤��� 🚀 👀

Pull requests list

Onnxruntime Weekly Sync 2026-05-01 automated Pull request is auto generated by actions dependencies Pull requests that update a dependency file onnxruntime PR changes interaction between MIGraphX and Onnxruntime skip bot checks Skips the Performance and Accuracy CI tests
#4836 opened May 1, 2026 by github-actions Bot Loading…
@TedThemistokleous
Extend problem cache with hardware provenance metadata
#4835 opened Apr 30, 2026 by danieyan-amd • Draft
6
Sym reshapes
#4832 opened Apr 29, 2026 by shivadbhavsar Contributor • Draft
1
Addition of MLSS MHA for GFX1201 as standalone header
#4831 opened Apr 29, 2026 by Zhaeong Contributor Loading…
23
CI: Automating workflow execution for internal contributors onlyy
#4830 opened Apr 29, 2026 by Muhamed-Husic Contributor Loading…
support stride > 1 case. ok-to-test
#4829 opened Apr 29, 2026 by weizhu12-amd • Draft
3
Fix literal promotion ok-to-test
#4826 opened Apr 28, 2026 by ivarusic-amd Contributor Loading…
8
support symbolic shape transpose, contiguous, as_shape
#4823 opened Apr 24, 2026 by shivadbhavsar Contributor Loading…
5
[AIMIGRAPHX-839] support symbolic shapes for broadcast ops
#4819 opened Apr 24, 2026 by shivadbhavsar Contributor Loading…
7
Enable static build of migraphx
#4817 opened Apr 23, 2026 by pfultz2 Collaborator Loading…
5
Rewrite skinny gemms to mul+reduce_sum ok-to-test
#4811 opened Apr 22, 2026 by pfultz2 Collaborator Loading…
6
Use fp32 FMA in channelwise conv
#4809 opened Apr 21, 2026 by klin2024 Contributor • Draft
1
Enable fp16 channelwise convolution ok-to-test
#4808 opened Apr 21, 2026 by klin2024 Contributor Loading…
7
Add fused MatMul operator ok-to-test
#4806 opened Apr 20, 2026 by ahsan-ca Contributor Loading…
@ahsan-ca
9
Bump CI to 7.2.2 ok-to-test
#4805 opened Apr 20, 2026 by causten Collaborator Loading…
28
Python API debug symbols
#4803 opened Apr 20, 2026 by CharlieL7 Collaborator Loading…
@CharlieL7
17
Add md5 sum function
#4801 opened Apr 20, 2026 by pfultz2 Collaborator Loading…
17
Add rocprofv3 and att trace library ok-to-test
#4797 opened Apr 17, 2026 by pfultz2 Collaborator Loading…
8
[AIMIGRAPHX-828] Cross Compile Pt 2: add env variable to enable cross compilation
#4795 opened Apr 17, 2026 by kahmed10 Collaborator Loading…
13
Rewrite mul reduce to use fdot2 instructions
#4787 opened Apr 15, 2026 by pfultz2 Collaborator • Draft
3
Improve yolov10n Performance Perf Improve
#4785 opened Apr 14, 2026 by ahsan-ca Contributor • Draft
@ahsan-ca
11
Add symbolic expression
#4782 opened Apr 13, 2026 by pfultz2 Collaborator Loading…
51
Remove gqa_rotary_embedding and use op builder in its place
#4777 opened Apr 10, 2026 by turneram Contributor Loading…
1
Add insert_slice op and remove concat_past_present
#4776 opened Apr 10, 2026 by turneram Contributor • Draft
[AIMIGRAPHX-885][AIMIGRAPGX-987] Use External Stream Contexts ok-to-test Perf Improve
#4775 opened Apr 10, 2026 by TedThemistokleous Collaborator Loading…
@TedThemistokleous
20
ProTip! What’s not been updated in a month: updated:<2026-04-01.