Commit Graph

  • 2a6a163e7d Fix test_gemm_multiply_multiply_wp_xdl_fp8 on gfx950 (#3191) jefyang1 2025-11-13 09:32:54 -06:00
  • 1d2d82ed69 Fix test_gemm_multiply_multiply_wp_xdl_fp8 on gfx950 (#3191) jefyang1 2025-11-13 09:32:54 -06:00
  • ca2ee0eb8a Fix test_gemm_multiply_multiply_wp_xdl_fp8 on gfx950 (#3191) jefyang1 2025-11-13 09:32:54 -06:00
  • 8ac9550ac8 make build config faster Philip Maybank 2025-11-13 14:56:24 +00:00
  • 95c1bb25e3 Remove the k_element_func and v_element_func from the pipeline since they are not used Qianfeng Zhang 2025-11-13 08:43:05 +00:00
  • 4ef9a192b7 make a start on RDNA / Navi specific doc Philip Maybank 2025-10-20 12:25:54 +01:00
  • 69829de237 Improve build infrastructure for generating doc Philip Maybank 2025-10-20 11:08:02 +01:00
  • c0c24584ec [CK_TILE] Improve F8F6F4 Scaled WarpGemm (#3197) Yi DING 2025-11-13 20:22:05 +08:00
  • 3b9fb5a00f fixing ambiguous shuffle definitions (#3175) Khushbu Agarwal 2025-11-12 23:44:12 -08:00
  • 2ecaf372d2 [CK TILE GEMM] Refactor block_scale_gemm examples (#3181) Cong Ma 2025-11-13 00:43:40 -07:00
  • 9e415a1486 Ck tile engine commons (#3166) Thrupti Raj Lakshmana Gowda 2025-11-13 00:56:18 -06:00
  • be9fd99dec chore(copyright): update copyright header for test_data directory (#3194) Aviral Goel 2025-11-12 19:07:28 -05:00
  • 5f91b33fce Add C++17 deprecation warning to CHANGELOG.md (#3203) John Afaganis 2025-11-12 17:05:53 -07:00
  • 7f67e9ead1 add permissions for /tmp folder (#3201) Illia Silin 2025-11-12 11:47:07 -08:00
  • 9aec41fd5d Wmma support for gemm_reduce (#3145) Enrico Degregori 2025-11-12 20:23:54 +01:00
  • db7224e067 Fixed impl Tianxing Wu 2025-11-13 14:02:24 +00:00
  • 53556bf6cb Merge commit '8d50001b939691134a0b078ed15a41e22ee08bd0' into develop assistant-librarian[bot] 2025-11-13 13:22:01 +00:00
  • f5eb722fbe [CK_TILE] Improve F8F6F4 Scaled WarpGemm (#3197) Yi DING 2025-11-13 20:22:05 +08:00
  • a05514ca58 [CK_TILE] Improve F8F6F4 Scaled WarpGemm (#3197) Yi DING 2025-11-13 20:22:05 +08:00
  • 8d50001b93 [CK_TILE] Improve F8F6F4 Scaled WarpGemm (#3197) Yi DING 2025-11-13 20:22:05 +08:00
  • 76e50bb65b Merge commit 'fb41a7b73be5b686611e3bc75668cb8025252d8d' into develop assistant-librarian[bot] 2025-11-13 08:15:17 +00:00
  • f4392ddaaf block_shape fixes Tianxing Wu 2025-11-13 08:14:52 +00:00
  • 1ec766b17d fixing ambiguous shuffle definitions (#3175) Khushbu Agarwal 2025-11-12 23:44:12 -08:00
  • 0366389527 fixing ambiguous shuffle definitions (#3175) Khushbu Agarwal 2025-11-12 23:44:12 -08:00
  • fb41a7b73b fixing ambiguous shuffle definitions (#3175) Khushbu Agarwal 2025-11-12 23:44:12 -08:00
  • fec8b3228b [CK TILE GEMM] Refactor block_scale_gemm examples (#3181) Cong Ma 2025-11-13 00:43:40 -07:00
  • c86dee45e0 [CK TILE GEMM] Refactor block_scale_gemm examples (#3181) Cong Ma 2025-11-13 00:43:40 -07:00
  • 6fd8ddabe7 [CK TILE GEMM] Refactor block_scale_gemm examples (#3181) Cong Ma 2025-11-13 00:43:40 -07:00
  • c36a71b050 Merge commit '9af30f04b65b8e50877d01ce8377a8cd581d462c' into develop assistant-librarian[bot] 2025-11-13 07:13:36 +00:00
  • 5c19f34cb4 Ck tile engine commons (#3166) Thrupti Raj Lakshmana Gowda 2025-11-13 00:56:18 -06:00
  • 537b3e1f00 Ck tile engine commons (#3166) Thrupti Raj Lakshmana Gowda 2025-11-13 00:56:18 -06:00
  • 9af30f04b6 Ck tile engine commons (#3166) Thrupti Raj Lakshmana Gowda 2025-11-13 00:56:18 -06:00
  • f03d7dcf6e Merge commit '797ddfa41e5e2c45f9eea9e6c969ba528e5a9c39' into develop assistant-librarian[bot] 2025-11-13 00:36:06 +00:00
  • 4c43e89a84 chore(copyright): update copyright header for test_data directory (#3194) Aviral Goel 2025-11-12 19:07:28 -05:00
  • 01b89f8cab chore(copyright): update copyright header for test_data directory (#3194) Aviral Goel 2025-11-12 19:07:28 -05:00
  • 797ddfa41e chore(copyright): update copyright header for test_data directory (#3194) Aviral Goel 2025-11-12 19:07:28 -05:00
  • 97dba6f3c5 Add C++17 deprecation warning to CHANGELOG.md (#3203) John Afaganis 2025-11-12 17:05:53 -07:00
  • 5652b8d145 Add C++17 deprecation warning to CHANGELOG.md (#3203) John Afaganis 2025-11-12 17:05:53 -07:00
  • 9342365713 Add C++17 deprecation warning to CHANGELOG.md (#3203) John Afaganis 2025-11-12 17:05:53 -07:00
  • b8b5709ccf enable preshuffle quant with permuteN khuagarw 2025-11-12 21:32:02 +00:00
  • 77527d2fa6 Merge commit '3784c0e7c395af214fdddd5f702691b354bfe8d4' into develop assistant-librarian[bot] 2025-11-12 20:14:45 +00:00
  • fbab772ad4 add permissions for /tmp folder (#3201) Illia Silin 2025-11-12 11:47:07 -08:00
  • 76306954ee add permissions for /tmp folder (#3201) Illia Silin 2025-11-12 11:47:07 -08:00
  • 3784c0e7c3 add permissions for /tmp folder (#3201) Illia Silin 2025-11-12 11:47:07 -08:00
  • e00db44d0c Wmma support for gemm_reduce (#3145) Enrico Degregori 2025-11-12 20:23:54 +01:00
  • 2f3dc0a119 Wmma support for gemm_reduce (#3145) Enrico Degregori 2025-11-12 20:23:54 +01:00
  • 7414a0f4d4 Wmma support for gemm_reduce (#3145) Enrico Degregori 2025-11-12 20:23:54 +01:00
  • 927e34b5db Merge branch 'develop' into ck-tile-docs Thomas Ning 2025-11-12 10:42:30 -08:00
  • 90e4b6bfe9 Merge commit '299c9bca1bee2ef77bb78878bcdd9d11a13564e5' into develop assistant-librarian[bot] 2025-11-12 16:14:54 +00:00
  • 881ddc5741 Update to the two trload pipeline to load whole Q-tile once through LDS on mi350 Qianfeng Zhang 2025-11-12 15:59:38 +00:00
  • c8c5a7e1c6 [CK_Tile] Pooling example readme update (#3174) Yashvardhan Agarwal 2025-11-12 17:30:20 +02:00
  • 0ca982f8d5 [CK_Tile] Pooling example readme update (#3174) Yashvardhan Agarwal 2025-11-12 17:30:20 +02:00
  • 299c9bca1b [CK_Tile] Pooling example readme update (#3174) Yashvardhan Agarwal 2025-11-12 17:30:20 +02:00
  • 6783e44e64 compile is fixed jukorhon/unified-attention Juuso Korhonen 2025-11-12 14:07:05 +00:00
  • 07bb33866b block_shape fixes Tianxing Wu 2025-11-12 14:00:51 +00:00
  • 3b56f0f0c3 fixed block sizes Tianxing Wu 2025-11-12 13:59:13 +00:00
  • 8f2e2886cd clear code ck_tile/fmha_block_scale ltqin 2025-11-12 06:10:03 +00:00
  • df55e264ad result right ltqin 2025-11-12 05:42:59 +00:00
  • 49aa7f3df5 rename struct tenpercent/dispatch Max Podkorytov 2025-11-11 21:21:36 -06:00
  • 9e6db6fda8 refactor captures Max Podkorytov 2025-11-11 21:17:19 -06:00
  • 113d7d65ac generalize on hot loop description Max Podkorytov 2025-11-11 21:01:38 -06:00
  • 98033a68ce Merge commit '40d2ed0f2a442026c57dc17e6e7bd281b6c2535c' into develop assistant-librarian[bot] 2025-11-12 02:42:51 +00:00
  • 97cb3abf33 [CK_TILE] Share partition index across threads and specify offset in load_tile()/async_load_tile()/load_tile_transpose() (#2905) Po Yen Chen 2025-11-12 10:26:14 +08:00
  • 7713c5071b [CK_TILE] Share partition index across threads and specify offset in load_tile()/async_load_tile()/load_tile_transpose() (#2905) Po Yen Chen 2025-11-12 10:26:14 +08:00
  • 40d2ed0f2a [CK_TILE] Share partition index across threads and specify offset in load_tile()/async_load_tile()/load_tile_transpose() (#2905) zhe_test Po Yen Chen 2025-11-12 10:26:14 +08:00
  • 15bee0499c refactor tile partitioner usage Max Podkorytov 2025-11-12 01:56:25 +00:00
  • 0f79fa5aed adding test khuagarw 2025-11-12 01:30:38 +00:00
  • 075c36b5f9 remove debugging statements khuagarw 2025-11-11 22:33:06 +00:00
  • c014babf51 Merge commit '92c1f4981ab1d081978c8f6132ca93949d4749e6' into develop assistant-librarian[bot] 2025-11-11 22:12:49 +00:00
  • 869bc5b77b adding preshuffle quant as new parameter and its associated new files khuagarw 2025-11-11 22:08:53 +00:00
  • a2a69e7649 [CK_BUILDER] Add grouped conv fwd ck tile traits (#3183) Bartłomiej Kocot 2025-11-11 22:55:33 +01:00
  • b122e12c91 [CK_BUILDER] Add grouped conv fwd ck tile traits (#3183) Bartłomiej Kocot 2025-11-11 22:55:33 +01:00
  • 92c1f4981a [CK_BUILDER] Add grouped conv fwd ck tile traits (#3183) Bartłomiej Kocot 2025-11-11 22:55:33 +01:00
  • f01853cf46 Add CK Tile Tutorials Folder with GEMM and COPY Kernel (#3038) Aviral Goel 2025-11-11 15:15:49 -05:00
  • efcd6297d4 Add CK Tile Tutorials Folder with GEMM and COPY Kernel (#3038) Aviral Goel 2025-11-11 15:15:49 -05:00
  • b145a5fe80 Add CK Tile Tutorials Folder with GEMM and COPY Kernel (#3038) Aviral Goel 2025-11-11 15:15:49 -05:00
  • ba43b54f9f Merge commit 'c54ecd905b07849076069d56c284472230564568' into develop assistant-librarian[bot] 2025-11-11 20:14:02 +00:00
  • a8d2ecc971 docs: update ckProfiler readme with selective building option (#3140) Aviral Goel 2025-11-11 14:27:33 -05:00
  • 4d69189324 docs: update ckProfiler readme with selective building option (#3140) Aviral Goel 2025-11-11 14:27:33 -05:00
  • c54ecd905b docs: update ckProfiler readme with selective building option (#3140) Aviral Goel 2025-11-11 14:27:33 -05:00
  • 9ec4b67288 chore(copyright): update copyright header for script directory (#3184) Aviral Goel 2025-11-11 14:26:01 -05:00
  • 9d49cab98b chore(copyright): update copyright header for script directory (#3184) Aviral Goel 2025-11-11 14:26:01 -05:00
  • ab68c9d384 chore(copyright): update copyright header for script directory (#3184) Aviral Goel 2025-11-11 14:26:01 -05:00
  • db12c41b56 Merge commit '1b1c46e508c1fd40a03f54114b6b78629032fb4f' into develop assistant-librarian[bot] 2025-11-11 17:12:49 +00:00
  • 13cf0bd17f [CK_TILE] Fix gemm_quant (#3186) linqunAMD 2025-11-12 00:23:57 +08:00
  • 31400ca622 [CK_TILE] Fix gemm_quant (#3186) linqunAMD 2025-11-12 00:23:57 +08:00
  • 1b1c46e508 [CK_TILE] Fix gemm_quant (#3186) linqunAMD 2025-11-12 00:23:57 +08:00
  • c1b5372db3 chore(copyright): update copyright header for tile_engine directory (#3180) Aviral Goel 2025-11-11 11:17:24 -05:00
  • d09313cf15 chore(copyright): update copyright header for tile_engine directory (#3180) Aviral Goel 2025-11-11 11:17:24 -05:00
  • 88e3212fcc chore(copyright): update copyright header for tile_engine directory (#3180) Aviral Goel 2025-11-11 11:17:24 -05:00
  • 2c7d1aba58 Bump commit ref for TheRock in workflows (#3189) Scott Todd 2025-11-11 07:44:38 -08:00
  • 4c757e5b4f Bump commit ref for TheRock in workflows (#3189) Scott Todd 2025-11-11 07:44:38 -08:00
  • aa1fb29aa1 Bump commit ref for TheRock in workflows (#3189) Scott Todd 2025-11-11 07:44:38 -08:00
  • ae4444dfba formatting (#3182) Khushbu Agarwal 2025-11-11 07:42:26 -08:00
  • a297885de5 formatting (#3182) Khushbu Agarwal 2025-11-11 07:42:26 -08:00
  • 06c651b100 formatting (#3182) Khushbu Agarwal 2025-11-11 07:42:26 -08:00
  • 8e23284922 Extend support for ak1 / bk1 WMMA (#3073) Enrico Degregori 2025-11-11 16:38:15 +01:00
  • f80e8dfaa8 Extend support for ak1 / bk1 WMMA (#3073) Enrico Degregori 2025-11-11 16:38:15 +01:00
  • 1c544abf57 Extend support for ak1 / bk1 WMMA (#3073) Enrico Degregori 2025-11-11 16:38:15 +01:00
  • 618ed6defb cmake list update Tianxing Wu 2025-11-11 14:35:26 +00:00