felix
817752cdb4
hotfix fix sorting int64 ( #2025 )
...
* fix sorting int64
* clang format
* fix example issue
* update WA issue #
---------
Co-authored-by: coderfeli <coderfeli@163.com >
Co-authored-by: carlushuang <carlus.huang@amd.com >
[ROCm/composable_kernel commit: a82f338fb9
2025-03-28 11:31:52 +08:00
carlushuang
f588e4b08e
[CK_TILE] return value with macro in ck_tile::kernel_launch API ( #1982 )
...
* return value with macro and revert the return value
* [CK-TILE] no-macro launch api solution (#1992 )
* no-macro solution
* address -Wcomma
---------
Co-authored-by: Max Podkorytov <4273004+tenpercent@users.noreply.github.com >
[ROCm/composable_kernel commit: e3c9886cdf
2025-03-20 11:00:29 -07:00
valarLip
3d06952a2b
hotfix fmoe build issue ( #1976 )
...
[ROCm/composable_kernel commit: 52b1cd7780
2025-03-13 15:11:59 +08:00
carlushuang
581c75f3b7
[CK_TILE] add moe-sorting MP kernel ( #1910 )
...
* moe sorting ex
* fix bug for race condition
* fix bug and optimze large expert
* fix
* optimize with sub_token_oneshot
* support skip empty tokens for expert sorting
* update moe_sorting
* tidy code
* support mp kernel
* hint mp
* remove use less code
* porting to example 15
---------
Co-authored-by: valarLip <340077269@qq.com >
[ROCm/composable_kernel commit: 353a612b44
2025-02-25 17:56:55 +08:00
valarLip
baf4710ef6
porting fmoe_sorting from moe_sorting ( #1884 )
...
* porting fmoe_sorting from moe_sorting
* pass default example test
* remod
[ROCm/composable_kernel commit: 0e5e29c4e2
2025-02-13 15:34:34 +08:00
carlushuang
8ed234da8c
[CK_TILE] moe sorting ex kernel to support expert > 128 ( #1840 )
...
* moe sorting ex
* fix bug for race condition
* fix bug and optimze large expert
* fix
* optimize with sub_token_oneshot
* support skip empty tokens for expert sorting
* update moe_sorting
* tidy code
[ROCm/composable_kernel commit: c0adab4850
2025-02-11 17:49:17 +08:00
carlushuang
2fec988802
[CK_TILE] Fix mock token id, support g1u1/g1u0 through same inline code block ( #1808 )
...
* fix mock token id
* prepare host for g1u1
* reformat inline-asm
* restructure uk_0
* restructure gate_up
* done
* change default to init=1
* update readme
* fix a bug in interleave pipeline
* rcp for silu
[ROCm/composable_kernel commit: 1ff50e78c6
2025-01-16 17:51:10 +08:00
carlushuang
4c4be7b14f
[CK_TILE] optimize moe-sorting kernel ( #1771 )
...
* opt moe sorting
* remove commented code
[ROCm/composable_kernel commit: 3d15f364b3
2024-12-23 10:59:02 +08:00
carlushuang
8acce2dee1
[CK_TILE] fused-moe first version ( #1634 )
...
* moe pipeline
* update code
* compile OK
* update
* update cpu reference
* update pipeline_gemm0
* compiler ok
* update pipeline
* rename to ex pipeline
* block-asm
* update
* update
* update first gemm ok
* compute correct
* update file structure
* update README
* update
* update
* update code
* update API
* return unsupport case
* add comment
* update readme
* update
* uncomment
* update
* fix build err
---------
Co-authored-by: valarLip <340077269@qq.com >
[ROCm/composable_kernel commit: 440e28b08f
2024-11-26 11:14:56 +08:00
