Skip to content

Issues: NVIDIA/Fuser

New issue

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

#

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

Already on GitHub? # to your account

204 Open 581 Closed
204 Open 581 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

Swizzle tiles in matmul without introducing larger grid due to nondivisible splits Matmuls
#3942 opened Feb 21, 2025 by jacobhinkle
@jacobhinkle
1
Allow separate sub-DAG for load and compute warp groups with warp-specialized circular buffering. Matmuls TMA
#3941 opened Feb 21, 2025 by rdspring1
@rdspring1
Test failed with Error replaying transforms in contiguous ID checker, expected iS10{9} to be in the active ID set.
#3919 opened Feb 19, 2025 by xwang233
1
@naoyam
2
Error with driver API's lazy load of cuStream ops
#3907 opened Feb 17, 2025 by samnordmann
2
MarkAliasesPrepare to recognize meta ops with DID loop split. allocation domain issues related to allocation domain support Multi-GPU
#3902 opened Feb 15, 2025 by wujingyue
2
Reuse user process group. Multi-GPU
#3901 opened Feb 15, 2025 by wujingyue
1
Fix ReorderShardedAxis and MakeReshardingContiguous for DID loop split. Multi-GPU
#3900 opened Feb 15, 2025 by wujingyue
1
Segfault after #3821
#3856 opened Feb 8, 2025 by wujingyue
@cowanmeg
4
Resize scheduler vectorization failure
#3855 opened Feb 8, 2025 by naoyam
@naoyam
Feature request: Consider privatization instead of forwarding in fusion segmentation Segmentation Issues related to nvFuser Segmentation
#3832 opened Feb 5, 2025 by naoyam
Feature request: Extend the privatization to improve segmentation Segmentation Issues related to nvFuser Segmentation
#3830 opened Feb 5, 2025 by naoyam
Feature request: Fusing sibling exprs in segmentation Segmentation Issues related to nvFuser Segmentation
#3829 opened Feb 5, 2025 by naoyam
Automate performant Hopper matmul H100 Perf improve performance on H100 Matmuls
#3819 opened Feb 4, 2025 by jacobhinkle
3 of 22 tasks
@jacobhinkle @rdspring1
3
supporting float32 on Scalar values
#3816 opened Feb 3, 2025 by jjsjann123
Unexpected performance regression with outer reduction
#3815 opened Feb 3, 2025 by naoyam
@liqiangxl
1
Reduction scheduler fails to recognize iter domains not captured by reference bug Something isn't working
#3811 opened Feb 3, 2025 by naoyam
@jjsjann123
Make FusionProfile object not a singleton and allow copying
#3771 opened Jan 28, 2025 by kshitij12345
LinearOp with multiple sharded dimensions
#3770 opened Jan 28, 2025 by samnordmann
2
pytest benchmark reporting incorrect benchmark time bug Something isn't working Python Benchmarks
#3753 opened Jan 23, 2025 by jjsjann123
9
Run the IdModel exact-ness validation as part of the launch-time validation idmodel
#3752 opened Jan 23, 2025 by naoyam
@naoyam
IOByte computation in benchmarks
#3721 opened Jan 16, 2025 by Priya2698
3
Redundant accesses due to missing predicates in resize
#3710 opened Jan 15, 2025 by naoyam
1
@naoyam
TensorDomain::flatten should squeeze broadcast IDs as done by the usual reshape transform
#3691 opened Jan 9, 2025 by naoyam
Optimize matrix multiplication performance using tma multicast Matmuls
#3689 opened Jan 9, 2025 by rdspring1
1 of 7 tasks
@rdspring1
15
Inlining error in Hopper matmul with AxisMapping and grid swizzling Matmuls
#3671 opened Jan 6, 2025 by jacobhinkle
@jacobhinkle
6
ProTip! Adding no:label will show everything without a label.