Skip to content

Pull requests: NVIDIA/Fuser

New pull request New
162 Open 3,102 Closed
162 Open 3,102 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

Align smem buffer for TMA store at 128B
#4071 opened Mar 13, 2025 by jacobhinkle • Draft
1
TMem check the stride of outer dims
#4070 opened Mar 13, 2025 by zasdfgbnm Loading…
3
Load Epilogue Inputs with LdMatrix in Hopper Matmul Scheduler Matmuls
#4069 opened Mar 13, 2025 by rdspring1 • Draft
3
Print local sizes and strides of each nn.Linear
#4067 opened Mar 12, 2025 by wujingyue • Draft
1
indexAccumulate python api
#4066 opened Mar 12, 2025 by jjsjann123 • Draft
1
Update SDPA flash attention API
#4065 opened Mar 12, 2025 by Priya2698 Loading…
6
Add a backprop test
#4064 opened Mar 12, 2025 by wujingyue Loading…
2
Adding IndexAccumulateOp
#4063 opened Mar 12, 2025 by jjsjann123 • Draft
2
Tensor-parallelize the DeepSeek V3 transformer layer
#4062 opened Mar 12, 2025 by wujingyue Loading…
2
add register count checks for warp specialization with register sharing
#4061 opened Mar 11, 2025 by liqiangxl Loading…
2
Make Hopper mma tests sparse
#4060 opened Mar 11, 2025 by zasdfgbnm Loading…
10
Simplify selfAllocationReplay
#4057 opened Mar 11, 2025 by wujingyue • Draft
3
s/reshape/set when no transforms are applied
#4056 opened Mar 10, 2025 by wujingyue Loading…
1
5
[WIP] Basic latency tests
#4053 opened Mar 9, 2025 by csarofeen • Draft
1
project persistent buffer to it producer if the buffer is the output of an upcast
#4051 opened Mar 9, 2025 by liqiangxl Loading…
15
supporting vectorized load on IndexSelectOp
#4048 opened Mar 8, 2025 by jjsjann123 Loading…
19
getOutputShardings checks all TVs to decide single-GPU vs multi-GPU
#4046 opened Mar 7, 2025 by wujingyue Loading…
3
[WIP] simple L2 model for setting grid swizzle and cta order
#4044 opened Mar 7, 2025 by jacobhinkle • Draft
1
Don't revert upcast for persistent schedulers to avoid increasing persistent buffer sizes
#4040 opened Mar 7, 2025 by liqiangxl Loading…
10
WIP
#4038 opened Mar 7, 2025 by zasdfgbnm • Draft
1
WIP
#4037 opened Mar 7, 2025 by zasdfgbnm • Draft
2
WIP
#4034 opened Mar 6, 2025 by zasdfgbnm • Draft
2
revise smem usage estimation
#4033 opened Mar 6, 2025 by liqiangxl • Draft
9
Automatically save MatmulParams in extra_info in benchmarks
#4031 opened Mar 6, 2025 by jacobhinkle Loading…
9
Add nvfuser benchmark executor and unify test_matmul.py
#4021 opened Mar 6, 2025 by jacobhinkle • Draft
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.