ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-29 19:28:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,820 Commits 776 Branches 40 Tags
d3fb5a9b8d02490cf16938644335df2a949d0ff3
Commit Graph

752 Commits

Author SHA1 Message Date
illsilin
d3fb5a9b8d fix clang format 2025-03-28 11:52:40 -07:00
lalala-sh
656a3657cb remove useless code change 2025-03-28 16:25:00 +08:00
root
7054d45579 remove useless changes 2025-03-28 08:21:42 +00:00
root
c9ce26837c Merge remote-tracking branch 'origin/develop' into moe_gemm_activation 2025-03-28 07:57:53 +00:00
felix
a82f338fb9 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>
 2025-03-28 11:31:52 +08:00
root
529a1732cd fp8 with act ready 2025-03-28 02:34:38 +00:00
lalala-sh
d0f3e87129 Merge remote-tracking branch 'origin/develop' into moe_gemm_activation 2025-03-28 10:02:27 +08:00
root
4f4bce30cf fuse gelu silu act in moe gemm1 2025-03-27 16:59:53 +08:00
coderfeli
bd4a8c71d4 i4 gemm2 ok and i4 gemm1 build 2025-03-27 06:41:31 +00:00
Rostyslav Geyyer
441343a23d Add MX FP4 device conversion tests (#1889) 
* Add conversion tests

* Fix ctor

* Fix nan logic

* Fix conversion logic

* Permute packed f4_t values

* Fix conversion to float, repack vector elements

* Fix device tests

* Permute elements in a vector

* Add a repro test

* Add a conversion for a repro test

* Update test vectors

* Update conversion

* Fix the test

* Update test vector generator

* Fix vector sr conversion

* Permute conversion args

* Update conversion

* Test

* Fix packing

* Simplify conversion function

* Pack conversion in a loop

* Pack conversion in a loop

* Pack another conversion in a loop

* Pack one more conversion in a loop

* Pack the last conversion in a loop

* Clean up

* Add printf to fix intrinsic

* Add a sw-based workaround
 2025-03-26 19:23:01 -05:00
Bartłomiej Kocot
54c81a1fcf Add support for GKCYX grouped conv fwd (#2015) 
* Add support for GKCYX grouped conv fwd

* fixes

* fix

* changelog

* Fixes
 2025-03-26 21:13:38 +01:00
coderfeli
9729c9e3f7 i4 gemm2 ok 2025-03-26 11:41:21 +00:00
coderfeli
6a0cc4aad1 gu fusion for m32 m64 ok 2025-03-26 05:58:22 +00:00
coderfeli
74d8ac608f gufusion compatible ok, fix warnings 2025-03-26 02:20:30 +00:00
Andriy Roshchenko
72d888821c MX GEMM examples with FP8, FP16, and E8M0 scales (#2016) 
* Add `scalar_type` specification for E8M0 exponent

* Specialize `nnvb_data_t_selector` for E8M0 exponent

* Remove partial specializations for `scalar_type` of `non_native_vector_base` template

* Reword command line helper string

* Create MX GEMM examples for different scales
 2025-03-25 15:33:03 -06:00
Max Podkorytov
1a58522f01 use fast path for sequence generation in old CK (#1993) 2025-03-25 11:28:44 -07:00
coderfeli
6ca5892256 gemm2 ok 2025-03-25 15:01:10 +00:00
ruanjm
d49abdaa87 [CK_TILE] Improve RMS/Layer Normalization 2 Pass Pipeline Performance (#1861) 
* 50ms -> 28ms

* Fix bug in non fuse_add_store cases

* Fine tuned setting for 2 pass pipeline

* adjust workload

* remove unnecessary change

* add layernorm

* Adding output quant and unquant results at the same time.

* fix test

* fix format

* tune for cases 128x640 and 128x1024

* bug ifx
 2025-03-25 20:09:45 +08:00
coderfeli
234b8d415c change code 2025-03-25 09:44:32 +00:00
coderfeli
0d266bfd65 add silu 2025-03-25 03:01:27 +00:00
coderfeli
2b15b67b3f acale ok 2025-03-25 02:52:04 +00:00
Illia Silin
d2eab23958 Split up data_type header. (#1996) 
* split fp64 vector data type

* add missing header

* move e8m0 structs

* split off numeric_utils header

* fix typo

* split off numeric limits header

* update data_type header

* fix clang format

* split off vector type header

* fix clang format

* fix typo for binary_inf
 2025-03-24 15:08:54 -07:00
Andriy Roshchenko
6660dc6b8e Introduce MX GEMM for FP8 data type (#2000) 2025-03-24 15:41:07 -06:00
MHYang-gh
c027637a8f Fix A/B lds transform (#2007) 2025-03-22 23:13:50 -07:00
Bartłomiej Kocot
5b0873c31a Fix split N for large images in groupd conv fwd (#2004) 
* Fix split N for large images in groupd conv fwd

* Fix comments
 2025-03-22 23:19:49 +01:00
coderfeli
b865e2cf83 silu ok 2025-03-22 14:03:45 +00:00
coderfeli
d69c1c9590 fuse silu 2025-03-21 07:31:49 +00:00
BingYuan.Zhou
5a0d693b86 fix ck_tile/basic_gemm build error (#1988) 2025-03-20 22:01:14 -07:00
Attila T. Áfra
c79bf11148 Fix compile errors on Windows and Linux (#2002) 
* Fix compile error on Windows (call to 'amd_wave_read_first_lane' is ambiguous)

* Fix compile error (no matching function for call to 'cast_to_f32_from_f8')
 2025-03-20 12:37:25 -07:00
carlushuang
e3c9886cdf [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>
 2025-03-20 11:00:29 -07:00
jakpiase
0e91d32c61 [CK_TILE] Switch to universal gemm for batched and grouped gemms (#1919) 
* switch to universal gemm for batched and grouped gemms

* added reviewer comments

* fixed grouped gemm tests
 2025-03-20 11:17:04 +01:00
rocking
b819c217e4 Sync the kname with instance name (#1989) 
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
 2025-03-20 00:06:45 +08:00
felix
7eaedeb36c Ck moe hot fix (#1979) 
* fix useless code and remove usless oob

* clang format

* fix coredump in e2e test

* fix2

* fix clang format

* fix output oob

* clang format

* rm useless comments

---------

Co-authored-by: coderfeli <coderfeli@163.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
 2025-03-19 22:58:27 +08:00
coderfeli
98cee8d02b fix merge 2025-03-18 05:45:04 +00:00
coderfeli
5f49b91237 merge develop 2025-03-18 04:49:40 +00:00
aledudek
5095906975 Async grouped gemm v3 (#1940) 
* Fully async grouped gemm

* Remove commented code

* Remvoe maybe_unused

* host kernel args

* Checkpoint segfault debugging...

* Working part1

* Working part2

* Remvoe comments...

* Use void ptr for gemm kernel host args

* Fix device_grouped_gemm_multiple_d_dl build issue

* Fix device_grouped_gemm_xdl build issue
 2025-03-17 16:42:43 +01:00
Bartłomiej Kocot
c2e4898b4b Grouped conv bwd data NGCHW (#1967) 
* Grouped conv bwd data NGCHW

* fixes

* fix

* Improvements

* Fix

* Fix

* add client example
 2025-03-17 13:32:00 +01:00
coderfeli
7dbdff9f9f moe sorting fix moebuf 2025-03-17 06:20:57 +00:00
coderfeli
5eaa36be18 mork to support 13w tokens 2025-03-17 01:45:34 +00:00
coderfeli
ef8c1333b9 use uint32 2025-03-17 01:45:09 +00:00
coderfeli
6c0e021235 revert v1 test 2025-03-17 01:39:57 +00:00
coderfeli
bccc5192cf fix uint32 2025-03-17 01:18:32 +00:00
coderfeli
da2659d502 input output all ok 2025-03-15 14:26:30 +00:00
coderfeli
d1e999c05c int64 index ok now 2025-03-15 13:28:49 +00:00
coderfeli
f911cf7396 impl int64 but result not correct 2025-03-14 13:01:07 +00:00
coderfeli
d4925e1637 fix output oob 2025-03-14 03:19:26 +00:00
carlushuang
3e81279d26 Reapply "[CK_TILE] support hdim=192/128 pair for deepseekv3 (#1961)" … (#1971) 
* Reapply "[CK_TILE] support hdim=192/128 pair for deepseekv3 (#1961)" (#1969)

This reverts commit 8cbcd3e0d0.

* fix codegen problem

* Update config.hpp

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
 2025-03-13 11:41:39 +08:00
illsilin
f8464d2087 fix clang format 2025-03-12 20:21:14 -07:00
coderfeli
d85c034977 fix2 2025-03-13 02:30:07 +00:00
coderfeli
8b05fa935d fix coredump in e2e test 2025-03-13 02:12:18 +00:00