Skip to content

Pull requests: NVIDIA/Fuser

New pull request New
114 Open 2,054 Closed
114 Open 2,054 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

Run user-scheduled fusions with input arguments on different devices.
#2769 opened Aug 7, 2024 by rdspring1 Loading…
1
Allow multiple outputs with different root domains for SDPAOp in ComputeAtMap
#2767 opened Aug 6, 2024 by Priya2698 Loading…
6
[WIP] Prioritize propagation of neighbors with a larger number of mapped root/logical domains
#2765 opened Aug 6, 2024 by naoyam • Draft
1
Pull allocation logic out of executor
#2757 opened Aug 4, 2024 by csarofeen • Draft
1
Move fusion executor files to their own directory
#2756 opened Aug 4, 2024 by csarofeen • Draft
disable shared memory persistent for 3D inner persistent scheduler
#2754 opened Aug 2, 2024 by liqiangxl • Draft
5
[WIP] Support contiguous indexing
#2752 opened Aug 2, 2024 by naoyam • Draft
1
Minor cleanup in executor.cpp
#2750 opened Aug 2, 2024 by csarofeen Loading…
18
Refactor Circular Buffer Pass
#2747 opened Aug 2, 2024 by rdspring1 Loading…
6
Revert "Promote hoisting of vectorize predicates"
#2742 opened Aug 1, 2024 by liqiangxl • Draft
2
Host irs/overlap: add number_of_streams and number_of_iterations
#2738 opened Aug 1, 2024 by samnordmann Loading…
4
[Multidevice tutorial]: sharding and DIDx
#2733 opened Jul 31, 2024 by samnordmann Loading…
5
Python API for SdpaBwdOp
#2727 opened Jul 31, 2024 by Priya2698 Loading…
1
Cleanup scheduleMmaOutputAllocation
#2726 opened Jul 31, 2024 by zasdfgbnm • Draft
Introduce multi matmul scheduler
#2719 opened Jul 30, 2024 by jacobhinkle • Draft
1
benchmarking thunder.jit, group norm
#2717 opened Jul 30, 2024 by liqiangxl Loading…
5
Re-write replaceSymbolicSizes using IdModel
#2714 opened Jul 30, 2024 by jacobhinkle • Draft
1
3
Fix order in sortAndRFactor
#2713 opened Jul 29, 2024 by liqiangxl • Draft
1
RS: Compose multiple MMA tiles into a single swizzle pattern
#2710 opened Jul 29, 2024 by zasdfgbnm Loading…
9
Prologue swizzle
#2705 opened Jul 29, 2024 by zasdfgbnm • Draft
Refactor test_python_frontend.py
#2701 opened Jul 27, 2024 by Priya2698 • Draft
8
Assert no bank conflict in hopper tests
#2700 opened Jul 27, 2024 by zasdfgbnm • Draft
1
Revise target threads, blocks, and unroll in outer grid reduction
#2681 opened Jul 25, 2024 by liqiangxl • Draft
fix replace symbolic size
#2672 opened Jul 24, 2024 by liqiangxl Loading…
3
use id model in extent substitution
#2668 opened Jul 23, 2024 by liqiangxl • Draft
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.