Skip to content

Pull requests: NVIDIA/Fuser

New pull request New
153 Open 3,065 Closed
153 Open 3,065 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

Add missing handle for EmbeddingFwdOp
#4019 opened Mar 6, 2025 by naoyam Loading…
1
3
Indexing for TMem ld and st
#4017 opened Mar 6, 2025 by zasdfgbnm Loading…
10
Check that warps are only accessing the subpartition of TMem that it can access
#4016 opened Mar 6, 2025 by zasdfgbnm Loading…
3
Tensor memory 32x32b data path pattern matching
#4015 opened Mar 5, 2025 by zasdfgbnm Loading…
2
Relax BFS target constraint in getInnerMmaLoopGroup
#4012 opened Mar 5, 2025 by jacobhinkle Loading…
1
3
use torch.nn.functional.rms_norm
#4011 opened Mar 5, 2025 by liqiangxl Loading…
4
Run a DeepSeek-V3 transformer block from Hugging Face
#4009 opened Mar 4, 2025 by wujingyue Loading…
3
Make sure IterDomain::resize generates non-symbolic IDs
#4007 opened Mar 4, 2025 by naoyam Loading…
5
WIP
#4006 opened Mar 4, 2025 by liqiangxl • Draft
update the default to 20
#4002 opened Mar 3, 2025 by crcrpar Loading…
Remove MmaOp::AxisMapping
#3995 opened Feb 28, 2025 by jacobhinkle • Draft
2
redo register sharing PR-3972
#3993 opened Feb 28, 2025 by liqiangxl • Draft
5
Translate MatmulOp and LinearOp on Hopper without AxisMapping
#3986 opened Feb 27, 2025 by jacobhinkle Loading…
6
add packed warp reduction
#3959 opened Feb 25, 2025 by liqiangxl • Draft
2
don't need to sync before write to smem in warp reduction runtime func
#3958 opened Feb 25, 2025 by liqiangxl Loading…
2
DID loop split for reshape without pre-sharding reshape propagation
#3953 opened Feb 24, 2025 by Priya2698 Loading…
14
Concretization replays loop transforms
#3950 opened Feb 23, 2025 by wujingyue • Draft
10
[WIP] Support scalar outputs from fusions
#3947 opened Feb 23, 2025 by csarofeen • Draft
4
Drafting polymorphic value support for dtensors.
#3940 opened Feb 21, 2025 by csarofeen • Draft
2
Debug zip
#3939 opened Feb 21, 2025 by zasdfgbnm Loading…
1
Multidimensional mesh
#3937 opened Feb 21, 2025 by cowanmeg Loading…
5
Expose backend type to python
#3928 opened Feb 20, 2025 by samnordmann Loading…
1
Add benchmarks for cross entropy loss
#3924 opened Feb 19, 2025 by protonu • Draft
2
Expose MultiDeviceExecutor and overlapped AG+matmul to python API
#3923 opened Feb 19, 2025 by samnordmann Loading…
31
avoid ublk tma out bound access
#3917 opened Feb 18, 2025 by liqiangxl • Draft
5
ProTip! What’s not been updated in a month: updated:<2025-02-06.