forked from NVIDIA/cutlass
-
Notifications
You must be signed in to change notification settings - Fork 70
Pull requests: intel/sycl-tla
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add split reduction kernel for Flash Attention decoding
#671
opened Dec 18, 2025 by
wuxun-zhang
Loading…
5 of 12 tasks
fix output shape for FMHA forward kernel
#670
opened Dec 18, 2025 by
wuxun-zhang
Loading…
1 of 3 tasks
Example changes for streamk and mixed dtype for new atom API
#665
opened Dec 17, 2025 by
rajprince-intel
Loading…
1 of 7 tasks
MXFP4/MXFP8/int4 weights support in CuTe interface MoE GEMM example
#640
opened Nov 21, 2025 by
sanchitintel
•
Draft
Added limitation check in gemm_with_epilogue_softmax example test
#636
opened Nov 19, 2025 by
kausikmaiti
•
Draft
[Experiment] Evaluate perf impact of striped vs. blocked SLM read/write 1D copy atoms
#631
opened Nov 15, 2025 by
sanchitintel
•
Draft
1 task done
Add CuTe Matrix Transpose tutorial
examples
Label for adding examples, complex kernels development using cutlass or cute APIS
information required
The PR requires more information to review them properly
Add python API for flash-attn
information required
The PR requires more information to review them properly
redesign required
Implementation require a redesign
wontfix
This will not be worked on
#558
opened Oct 13, 2025 by
YangKai0616
Loading…
Rewrite mma unit tests
Tests
For Unit tests and Benchmark tests and general validation specific changes
#557
opened Oct 13, 2025 by
yuanhang-dev
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.