Skip to content

Pull requests: NVIDIA/Fuser

New pull request New
131 Open 2,916 Closed
131 Open 2,916 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

disable PreBroadcastMmaBiasNeg on blackwell
#3820 opened Feb 4, 2025 by liqiangxl Loading…
2
don't unroll if for loop has reduction
#3818 opened Feb 4, 2025 by liqiangxl • Draft
4
Use PredicateType::ElectSync with TMA store expressions Matmuls
#3814 opened Feb 3, 2025 by rdspring1 • Draft
2
[DO NOT MERGE] Add some llama latency scripts for testing
#3813 opened Feb 3, 2025 by csarofeen • Draft
1
Implement persistent matmul scheduling
#3812 opened Feb 3, 2025 by jacobhinkle Loading…
2
Deallocate TMem when done using it
#3806 opened Jan 31, 2025 by zasdfgbnm Loading…
9
use buffer storage params
#3804 opened Jan 31, 2025 by liqiangxl • Draft
1
[WIP] Comms through cudaIpc
#3799 opened Jan 30, 2025 by samnordmann • Draft
3
[WIP] ExprEvalExecutor Speedup
#3796 opened Jan 29, 2025 by csarofeen • Draft
2
Set __launch_bounds__ in kernel whenever we are able
#3794 opened Jan 29, 2025 by jacobhinkle Loading…
13
Demonstrates autograd integration with NVFuser multidevice
#3787 opened Jan 29, 2025 by syed-ahmed Loading…
11
Use F.rms_norm in benchmarks
#3783 opened Jan 29, 2025 by Priya2698 Loading…
1
[CI Testing] For Issue #3629
#3767 opened Jan 28, 2025 by Priya2698 • Draft
3
Move getConsumerPosAlignedToProducerCA to MaxPosCalculator
#3766 opened Jan 28, 2025 by naoyam Loading…
8
[WIP] Scheduling propagation through broadcast IDs
#3763 opened Jan 27, 2025 by naoyam • Draft
2
Add a few benchmarks for concatenation. Indexing Ops Thunder
#3751 opened Jan 23, 2025 by tfogal Loading…
52
Move RNG logic out of codegen to a lowering pass.
#3749 opened Jan 23, 2025 by csarofeen Loading…
8
[WIP] Loop promotion for cyclic graphs
#3747 opened Jan 23, 2025 by naoyam • Draft
2 tasks done
1
16
Rng devel debug
#3744 opened Jan 22, 2025 by csarofeen • Draft
4
[Do not merge] Overlap benchmark: AG+GEMM distributed matmul with HostIr and ParallelType::Stream
#3719 opened Jan 16, 2025 by samnordmann Loading…
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
ProTip! Type g i on any issue or pull request to go back to the issue listing page.