Skip to content

Pull requests: NVIDIA/Fuser

New pull request New
124 Open 2,865 Closed
124 Open 2,865 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

[WIP] Loop promotion for cyclic graphs
#3747 opened Jan 23, 2025 by naoyam • Draft
2
[WIP] Add extra validation for IdModel
#3746 opened Jan 23, 2025 by naoyam • Draft
2
Update PR review system prompt
#3745 opened Jan 23, 2025 by xwang233 Loading…
2
Rng devel debug
#3744 opened Jan 22, 2025 by csarofeen • Draft
3
fixing rope pytest benchmark grad accumulation
#3743 opened Jan 22, 2025 by jjsjann123 • Draft
7
DID loop split for matmul + allreduce
#3742 opened Jan 21, 2025 by Priya2698 Loading…
15
add 1D TMA UBLKCP
#3739 opened Jan 21, 2025 by liqiangxl Loading…
5
Lower stream-parallelized LinearOp into Host IR AG+GEMM overlap algo
#3736 opened Jan 20, 2025 by samnordmann Loading…
6
Int based RNG
#3733 opened Jan 19, 2025 by csarofeen • Draft
1
[Do not merge] Overlap benchmark: AG+GEMM distributed matmul with HostIr and ParallelType::Stream
#3719 opened Jan 16, 2025 by samnordmann Loading…
In the permissive bfs traversal, don't allow reverse traversal
#3717 opened Jan 16, 2025 by naoyam Loading…
2
Reapply #3621
#3714 opened Jan 16, 2025 by wujingyue • Draft
3
Avoid redundancy with resize ops
#3713 opened Jan 15, 2025 by naoyam • Draft
1
3
Omit the where predicate of pad when found safe to do so rope
#3708 opened Jan 14, 2025 by naoyam • Draft
3
[DO NOT REVIEW] Testing main
#3698 opened Jan 12, 2025 by csarofeen Loading…
2
[WIP] Extending forwarding of fusion segmenter
#3659 opened Dec 31, 2024 by naoyam • Draft
3
[WIP] Resize scheduler update
#3657 opened Dec 31, 2024 by naoyam • Draft
1
Split Hopper MMA by warp-tile before instruction tile on hold This issue should be revisited in the future
#3642 opened Dec 24, 2024 by jacobhinkle Loading…
1
17
Support outer reduction scheduler with SOL autotuning Autotune Generate heuristics through machine learning models.
#3618 opened Dec 19, 2024 by rdspring1 Loading…
1
Fix matmul incorrect results when k dim for CTA tile is a multiple of 16 Matmuls
#3616 opened Dec 19, 2024 by rdspring1 • Draft
5
Support TMA with 64-bit indexing
#3599 opened Dec 16, 2024 by jacobhinkle Loading…
1
4
[wgmma] Insert commit_group and wait_group after mma_async Matmuls
#3573 opened Dec 11, 2024 by jacobhinkle • Draft
1
9
[do not merge] nsight compute for #3563 Matmuls
#3568 opened Dec 11, 2024 by zasdfgbnm • Draft
[do not merge] Register stealing Matmuls
#3566 opened Dec 11, 2024 by zasdfgbnm • Draft
2
[Do not merge] Pull elect-sync predicate out Matmuls
#3564 opened Dec 11, 2024 by zasdfgbnm • Draft
ProTip! Follow long discussions with comments:>50.