forked from NVIDIA/cutlass
-
Notifications
You must be signed in to change notification settings - Fork 31
Pull requests: codeplaysoftware/cutlass-sycl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Move FP8 conversion to NumericArrayConverter
release
#424
opened Jun 11, 2025 by
aacostadiaz
Loading…
Unify interface for Flash Attention Decode
#423
opened Jun 11, 2025 by
muhammad-tanvir-1211
Loading…
support different scale/zero data type for mixed input mma
release
#420
opened Jun 11, 2025 by
taozha2
Loading…
Adding Fp8 input support for flash attention prefill
release
#419
opened Jun 11, 2025 by
mehdi-goli
Loading…
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…
RFC: test out new syntax for launch with type deduction
#305
opened Apr 12, 2025 by
rolandschulz
Loading…
ProTip!
Updated in the last three days: updated:>2025-06-10.