This website requires JavaScript.
Explore
Help
Register
Sign In
ROCm
/
composable_kernel
Watch
1
Star
0
Fork
0
You've already forked composable_kernel
mirror of
https://github.com/ROCm/composable_kernel.git
synced
2026-07-15 11:34:54 +00:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
facd5560e7616b242ea40930f0af4bb4c595ec10
composable_kernel
/
include
/
ck
/
tensor_operation
/
gpu
History
mtgu0705
facd5560e7
added new int4->fp8 conversion, performance has been improved by 6%.
2025-03-24 18:00:58 +08:00
..
block
fixed BK1 value when use bpreshuffle and HotLoopScheduler
2025-03-20 17:24:21 +08:00
device
Async grouped gemm v3 (
#1940
)
2025-03-17 16:42:43 +01:00
element
added new int4->fp8 conversion, performance has been improved by 6%.
2025-03-24 18:00:58 +08:00
grid
Ck moe hot fix (
#1979
)
2025-03-19 22:58:27 +08:00
thread
Ck moe hot fix (
#1979
)
2025-03-19 22:58:27 +08:00
warp
Remove CK_USE_AMD_MFMA_GFX950 (
#1935
)
2025-03-04 10:32:25 -08:00
