Commit Graph

  • 4e0c0435d3 3 v0.03 CreativeHong 2026-06-28 18:02:06 +0800
  • 37329c7b56 Merge remote-tracking branch 'origin/v0.02' into v0.02 CreativeHong 2026-06-28 17:55:18 +0800
  • 564d70dd60 Merge remote-tracking branch 'origin/v0.02' into v0.02 v0.02 CreativeHong 2026-06-28 17:55:18 +0800
  • a2e7a9b949 Merge remote-tracking branch 'origin/v0.02' into v0.02 CreativeHong 2026-06-28 17:54:36 +0800
  • f0b7f788df Merge remote-tracking branch 'origin/v0.02' into v0.02 CreativeHong 2026-06-28 17:54:36 +0800
  • 4643721513 Merge remote-tracking branch 'origin/v0.02' into v0.02 CreativeHong 2026-06-28 17:53:22 +0800
  • a8fb65eca8 Merge remote-tracking branch 'origin/v0.02' into v0.02 CreativeHong 2026-06-28 17:53:22 +0800
  • 0491c65f9b Merge remote-tracking branch 'origin/v0.01' into v0.01 CreativeHong 2026-06-28 17:44:14 +0800
  • f8e9b88ec6 Merge remote-tracking branch 'origin/v0.01' into v0.01 v0.01 CreativeHong 2026-06-28 17:44:14 +0800
  • 1e52ba33b0 完成了issue2和issue3,尚未测试 CreativeHong 2026-06-28 17:43:27 +0800
  • baa74f21a2 完成了issue2和issue3,尚未测试 CreativeHong 2026-06-28 17:43:27 +0800
  • 412c564d8e feat: implement tiled softmax and vector_add kernels CreativeHong 2026-06-28 17:39:44 +0800
  • 287867a34e build: add optional tilelang-metax validation mode main feature/implement-kernels yutianyu 2026-05-13 10:08:28 +0000
  • 9afe211d65 docs: streamline README and guides yutianyu 2026-05-13 16:08:21 +0800
  • 7c6a5ed9aa feat: integrate CUTLASS CuTe-optimized copy for L40 (SM89) yutianyu 2026-05-12 18:34:32 +0800
  • c8ad11c277 refactor: unify elementwise runtime helpers yutianyu 2026-05-12 16:23:06 +0800
  • 9271fed062 feat: add reusable elementwise relu support yutianyu 2026-05-12 11:30:19 +0800
  • a2f198f4d1 Initial commit master wawahejun 2026-05-11 16:38:52 +0800
  • 757dbbec74 refactor: split operator headers into public and detail layers yutianyu 2026-05-08 11:18:47 +0800
  • 6e02c3eb55 feat: add MACA-based MetaX backend support yutianyu 2026-05-06 04:08:49 +0000
  • ec8ed33b27 docs: add detailed info md yutianyu 2026-05-04 23:39:52 +0800
  • 6d1f205610 refactor: scaffold phase1 kernel skeletons yutianyu 2026-05-04 23:37:20 +0800
  • 7d94bb17f9 docs: add phase1 kernel writing guide yutianyu 2026-05-04 23:36:40 +0800
  • 9147a4821d feat: add kernel-focused benchmark timing harness yutianyu 2026-05-04 23:35:57 +0800
  • 346fd7db12 refactor: rename op tests and update benchmark entrypoint yutianyu 2026-05-04 23:35:28 +0800
  • a2cda3fda7 feat: add more shared test cases yutianyu 2026-05-04 21:15:31 +0800
  • e9a4c87564 docs: update guides for refactored python layout yutianyu 2026-05-04 19:37:39 +0800
  • dcf4d25896 refactor: split runtime internals and testing package yutianyu 2026-05-04 19:37:28 +0800
  • 1c5b1db200 refactor: consolidate benchmark entrypoint yutianyu 2026-05-04 19:16:49 +0800
  • 1368fa2886 docs: add Chinese README and operator guide yutianyu 2026-05-04 19:16:21 +0800
  • aec1073394 refactor: restructure Python package layout yutianyu 2026-05-04 18:48:58 +0800
  • fa2608e9b6 build: remove YAML-driven operator registration yutianyu 2026-05-04 18:48:25 +0800
  • e255552a94 chore: add requirements.txt and update README setup/validate instructions yutianyu 2026-05-02 03:08:23 +0800
  • 1759575ea7 refactor: organize per-operator test runners yutianyu 2026-05-02 02:49:29 +0800
  • 246e21f3d1 feat: unify example backends and shared test cases yutianyu 2026-05-02 02:48:05 +0800
  • 347421d28b refactor: reorganize operator benchmarks yutianyu 2026-05-02 02:01:16 +0800
  • e4ce213d65 refactor: split tilelang student kernels yutianyu 2026-05-02 02:00:05 +0800
  • 9db9af67b8 refactor: split nvidia operator kernels yutianyu 2026-05-02 01:23:11 +0800
  • fb59a60034 test: cover TileLang copy templates yutianyu 2026-05-02 01:10:53 +0800
  • dbe054c876 feat: add TileLang copy mode templates yutianyu 2026-05-02 01:09:59 +0800
  • 449075499b test: add runtime correctness and benchmark coverage yutianyu 2026-05-02 00:42:36 +0800
  • ce30e4b195 feat: scaffold operator runtime backends yutianyu 2026-05-02 00:42:20 +0800
  • 529e7fc7b7 docs: add training runtime guide and examples yutianyu 2026-05-02 00:41:54 +0800
  • ddbbc09019 chore: add project ignore rules yutianyu 2026-05-02 00:26:42 +0800
  • df83aafc05 feat: add cnb yutianyu 2026-04-29 23:57:25 +0800