Skip to content

Pull requests: codeplaysoftware/cutlass-sycl

New pull request New
22 Open 371 Closed
22 Open 371 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Adding Fp8 input support for flash attention prefill
#419 opened Jun 11, 2025 by mehdi-goli Loading…
Add data type conversion support in epilogue release
#418 opened Jun 10, 2025 by aacostadiaz Loading…
Template atoms
#417 opened Jun 10, 2025 by t4c1 • Draft
A(16bits)xB(8bits) GEMM release
#416 opened Jun 10, 2025 by jiyang1011 Loading…
2
Split example for prefill attention with cachedkv
#409 opened Jun 6, 2025 by aacostadiaz Loading…
2
Add tests and benchmark configurations for BF16 | FP16 output for Flash Decode
#408 opened Jun 5, 2025 by muhammad-tanvir-1211 Loading…
Add Paged Attention Configurations to Flash Decode
#405 opened Jun 4, 2025 by muhammad-tanvir-1211 • Draft
Add Paged Attention for Flash Attention Decode release
#403 opened Jun 2, 2025 by muhammad-tanvir-1211 Loading…
10
Fix for U8 transpose release
#392 opened May 27, 2025 by t4c1 Loading…
Update PVC drivers
#391 opened May 26, 2025 by aacostadiaz Loading…
8
Add documentation for 2D copy
#386 opened May 21, 2025 by aacostadiaz Loading…
15
Cutlass 4.0
#385 opened May 20, 2025 by aacostadiaz • Draft
Enable prefetch iteration
#382 opened May 19, 2025 by t4c1 Loading…
24
enable splitk for mixed precision gemm release
#381 opened May 19, 2025 by taozha2 Loading…
Check the WarpLayout provided to TiledMMAHelper
#377 opened May 15, 2025 by joeatodd Loading…
1
Add unit test for FP16 MMA
#368 opened May 12, 2025 by aacostadiaz Loading…
FP8 Grouped GEMM CollectiveMma release
#351 opened May 1, 2025 by sanchitintel • Draft
14
add gemm with rmsnorm
#321 opened Apr 22, 2025 by yuankuns Loading…
18
add int8/tf32 transpose A copy traits
#319 opened Apr 21, 2025 by taozha2 Loading…
15
Pure FP8 (W8A8) GEMM support (draft)
#306 opened Apr 14, 2025 by jiyang1011 Loading…
10
RFC: test out new syntax for launch with type deduction
#305 opened Apr 12, 2025 by rolandschulz Loading…
7
Enable SM90 via sycl-cuda-compat
#276 opened Mar 24, 2025 by FMarno Loading…
@Ruyk
16
ProTip! Add no:assignee to see everything that’s not assigned.