Skip to content

Issues: ROCm/AMDMIGraphX

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

370 Open 828 Closed
370 Open 828 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Add SD3 to DLM for both MIGX and TRT
#3459 opened Sep 18, 2024 by causten
@kahmed10
Add llama2 with KV-cache example
#3458 opened Sep 18, 2024 by turneram
@turneram
Add llama2 with KV-cache to DLM
#3457 opened Sep 18, 2024 by turneram
@turneram
Compare llama2 performance with/without KV-cache
#3456 opened Sep 18, 2024 by turneram
@turneram
Add compile pass for hipblaslt
#3455 opened Sep 18, 2024 by ahsan-ca
@ahsan-ca
Improve driver verify through bisection
#3447 opened Sep 16, 2024 by richagadgil
@richagadgil
Use GPU intrinsics and HIP types for FP8 for MIGX JIT kernels FP8 issues related to FP8 implemenation
#3442 opened Sep 13, 2024 by CharlieL7
@CharlieL7
[Issue]: accuracy_checker.py is not within tolerance for bert_large_uncased_1_fp16_gpu.onnx
#3440 opened Sep 13, 2024 by dhernandez0
blas_shape: GPU_GEMM: Batch dimension is not collapsible bug Something isn't working Torch Benchmarks
#3439 opened Sep 12, 2024 by shivadbhavsar
@shivadbhavsar
Improve simplify_algebra to find more horizontal fusion opportunities
#3432 opened Sep 10, 2024 by kahmed10
1
@aarushjain29
Update formatter github action to make suggestions Continous Integration Pull request updates parts of continous integration pipeline enhancement New feature or request
#3431 opened Sep 10, 2024 by CharlieL7
Add padding for preloading tiles into LDS for transpose
#3427 opened Sep 6, 2024 by CharlieL7
Figure out the encoding for fp8 in numpy (numpy does not have a way currently) FP8 issues related to FP8 implemenation
#3422 opened Sep 6, 2024 by CharlieL7
Add group convolution support for fp8 (needs MLIR update) FP8 issues related to FP8 implemenation
#3421 opened Sep 6, 2024 by CharlieL7
Figure out why test_gemm_add verify test is inaccurate for fp8 bugfix Fixes a bug found in the code. FP8 issues related to FP8 implemenation
#3420 opened Sep 6, 2024 by CharlieL7
Update OCP FP8 support with hipblaslt support FP8 issues related to FP8 implemenation roadmap Tasks to finish for a release
#3419 opened Sep 6, 2024 by CharlieL7
@CharlieL7
Perf regressions after moving auto_contiguous before lowering pass
#3415 opened Sep 4, 2024 by kahmed10
2 tasks
@pfultz2
Remove padding only when used with pooling
#3414 opened Sep 4, 2024 by causten
@pfultz2
JIRA Ticket: GLIBCXX_3.4.30 not found
#3405 opened Aug 28, 2024 by ahsan-ca
@ahsan-ca
2
Improve performance of GQA sub-operators on GPU
#3396 opened Aug 21, 2024 by turneram
@turneram
Enable contrib ops for Llama2 in ORT and run end-to-end workflow
#3395 opened Aug 21, 2024 by turneram
@turneram
Debug end-to-end accuracy of Llama2
#3394 opened Aug 21, 2024 by turneram
@turneram
Support microsoft contrib ONNX operator MatMulNBits UAI
#3390 opened Aug 19, 2024 by hgaspar
Verification failure with bert_large model
#3388 opened Aug 19, 2024 by djramic
Refactor mlir rewrites into single function
#3384 opened Aug 16, 2024 by umangyadav
ProTip! Exclude everything labeled bug with -label:bug.