Commit Graph

1499 Commits

Author SHA1 Message Date
PoYen, Chen
443a528adc Add block_table kernel args for appendkv kernel 2024-08-07 04:27:15 +00:00
PoYen, Chen
15d0034a64 Add paged-kv codegen logic for appendkv kernels 2024-08-07 04:19:45 +00:00
PoYen, Chen
b98985262d Add missing kernel arguments for group mode 2024-08-06 14:54:07 +00:00
PoYen, Chen
db31475e07 Unify origin 2024-08-06 08:37:29 +00:00
PoYen, Chen
bd0d2f3975 Add batch_stride_k/batch_stride_v in group mode 2024-08-06 08:02:43 +00:00
PoYen, Chen
faf6b0e8ab Fix wrong origin for bias 2024-08-06 08:02:08 +00:00
PoYen, Chen
12da00c3be Use 128 as minimus page_block_size 2024-08-06 03:20:29 +00:00
PoYen, Chen
f9e2bafd10 Make sure we always start reading complete tile 2024-08-06 03:13:57 +00:00
PoYen, Chen
4fed268723 Move code after decide seqlen_q/seqlen_k 2024-08-06 01:39:49 +00:00
PoYen, Chen
8779716403 Fix uneven split checking logic 2024-08-06 01:17:14 +00:00
PoYen, Chen
77dac7775c Move V tile through TileWindowNavigator 2024-08-05 22:36:52 +00:00
PoYen, Chen
ab086bdb76 Simplify more make_tile_window() overloads 2024-08-05 22:16:24 +00:00
PoYen, Chen
bb78353264 Remove ununnecessary data members 2024-08-05 21:52:59 +00:00
PoYen, Chen
3fc7279519 Disable calling fmha_fwd() 2024-08-05 21:36:52 +00:00
PoYen, Chen
8fea4139df Fix tile window navigation bugs 2024-08-05 21:34:15 +00:00
PoYen, Chen
ecaaa6f136 Simplify TileWindowNavigator interfaces 2024-08-05 16:31:31 +00:00
PoYen, Chen
1c9d77b606 Introduce 'TileWindowNavigator' types 2024-08-05 15:58:41 +00:00
PoYen, Chen
55b77cf962 Add another make_tile_window() 2024-08-05 15:57:03 +00:00
PoYen, Chen
24cb604373 Add copy_const<> type trait 2024-08-05 15:56:15 +00:00
PoYen, Chen
90d84eaeae Fix seqlen_k_min for pre-fill case (1 -> 0) 2024-08-04 02:53:40 +00:00
PoYen, Chen
381f7e90e0 Merge branch 'develop' into feature/fmha-fwd-appendkv 2024-08-04 02:12:20 +00:00
PoYen, Chen
baf4a612f0 Fix wrong kernel name 2024-08-02 10:26:47 +00:00
PoYen, Chen
db95d25d36 Launch splitkv kernel if given page_block_size 2024-08-02 10:26:09 +00:00
PoYen, Chen
e7969b9fd2 Add template argument 'kIsPagedKV' for splitkv kernels 2024-08-02 10:14:51 +00:00
Illia Silin
d311c95396 Add compiler flags for ROCm versions 6.2+ (#1429)
* add compiler flags to fix compiler issues

* fix typo.

* disable test_smfmac_op on all devices except gfx942

* specify full path to compiler in CI
2024-08-01 08:27:52 -07:00
Sam Wu
6648fd3b04 Update doc requirements (#1423) 2024-07-31 07:42:42 -07:00
zjing14
f31e8dfa80 [HotFix] Fixed a typo in profile_gemm_multiply_multiply (#1425)
* fixed a typo

* clean

---------

Co-authored-by: Jing Zhang <jizhan@fb.com>
2024-07-31 07:19:17 -07:00
arai713
d32997a792 Codegen: isSupportedArgument check (#1417)
* added isSupportedArgument check into codegen device op

* adding function call

* remove commented code
2024-07-31 07:12:15 -07:00
carlushuang
b3f86e79dd workaround rocm-6.2 compiler issue (#1421) 2024-07-31 16:03:59 +08:00
PoYen, Chen
3f7199873c Merge branch 'develop' into feature/fmha-fwd-appendkv 2024-07-31 04:42:41 +00:00
Illia Silin
b527cad4a5 add docker for rocm6.2_rc4 compiler (#1424) 2024-07-30 11:55:33 -07:00
Bartłomiej Kocot
33b399cc15 Revert Revert Support access per groups and filter2x3 in grouped conv fwd (#1382) (#1406) (#1415) 2024-07-30 18:36:04 +02:00
Po Yen Chen
08d82ee264 Merge branch 'develop' into feature/fmha-fwd-appendkv 2024-07-30 17:55:09 +08:00
dependabot[bot]
b9ba5b2676 Bump rocm-docs-core from 1.6.0 to 1.6.1 in /docs/sphinx (#1420)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.6.0 to 1.6.1.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.6.0...v1.6.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-07-26 14:47:19 -07:00
PoYen, Chen
e688d99495 Merge remote-tracking branch 'origin/develop' into feature/fmha-fwd-appendkv 2024-07-26 07:14:59 +00:00
PoYen, Chen
94f430de32 Update rotary_dim range in smoke_test_fwd.sh 2024-07-26 07:13:25 +00:00
PoYen, Chen
c1c50ee498 Enlarge KPerThread for rotary_interleaved=false 2024-07-26 07:09:53 +00:00
PoYen, Chen
d41ff70db5 Enlarge rotary_dim limit (8 -> 16) 2024-07-26 06:51:24 +00:00
trixirt
733f33af78 Introduce cmake USE_GLIBCXX_ASSERTIONS option (#1404)
A standard option in Fedora packaging that is used to check
the correctness of c++ use of the standard c++ library.

Signed-off-by: Tom Rix <trix@redhat.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
2024-07-25 19:28:17 -07:00
zjing14
105bd708c7 Add rotating buff for gemm_multi_d (#1411)
* add rotating_buff for gemm_multi_d

* format

* Update flush_cache.hpp

* Update gtest.cmake

---------

Co-authored-by: Jing Zhang <jizhan@fb.com>
Co-authored-by: Haocong WANG <haocwang@amd.com>
2024-07-25 23:21:21 +08:00
dependabot[bot]
1208082e53 Bump rocm-docs-core from 1.5.1 to 1.6.0 in /docs/sphinx (#1416)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.5.1 to 1.6.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.5.1...v1.6.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-07-24 22:56:29 -07:00
Andriy Roshchenko
4a8a1befd5 Adding more instances of grouped convolution 3d forward for FP8 with ConvScale+Bias element-wise operation. (#1412)
* Add CMakePresets configurations.

* Add binary elementwise ConvScaleAdd and an example.

* Numerical verification of results.

Observed significant irregularities in F8 to F32 type conversions:
```log
ConvScaleAdd: float=145.000000   f8_t=160.000000    e=144.000000
ConvScaleAdd: float=97.000000   f8_t=96.000000    e=104.000000
ConvScaleAdd: float=65.000000   f8_t=64.000000    e=72.000000
```

* Implemented ConvScaleAdd + Example.

* Add ConvScale+Bias Instances

* Add Client Example for ConvScale+Bias

* Fix number of bytes in an example..

* Cleanup.
2024-07-24 15:49:55 -05:00
Bartłomiej Kocot
ffabd70a15 Add support for half_t and bfloat to reduction operations (#1395)
* Add support for half_t and bfloat to reduction operations

* Fix bhalf convert

* Next fix bf16
2024-07-24 12:12:37 -05:00
dependabot[bot]
33b2a2bdf5 Bump rocm-docs-core from 1.5.0 to 1.5.1 in /docs/sphinx (#1414)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.5.0 to 1.5.1.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.5.0...v1.5.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-07-24 07:10:50 -07:00
PoYen, Chen
4280a07d2a Refine pipeline padding settings 2024-07-24 11:37:56 +00:00
PoYen, Chen
f053ae2b5b Add missing init code 2024-07-24 07:12:06 +00:00
PoYen, Chen
bd28e96425 Remove no-longer used method in pipeline 2024-07-24 06:59:45 +00:00
PoYen, Chen
c50c36a07f Re-arrange the 'set +x' command 2024-07-24 06:56:53 +00:00
PoYen, Chen
8fb015b83f Remove more debug statements 2024-07-24 06:48:40 +00:00
PoYen, Chen
5c733dc568 Remove debug statements 2024-07-24 06:47:52 +00:00