张壹 zhangyiss
  • Joined on 2024-09-10
zhangyiss synced commits to rerun-295 at zhangyiss/toml11 from mirror 2025-12-03 01:08:14 +08:00
zhangyiss synced commits to main at zhangyiss/toml11 from mirror 2025-12-03 01:08:13 +08:00
504692db77 feat [skip ci]: update single_include
bd1bae2b51 feat: change some unreleased features as ext
Compare 2 commits »
zhangyiss synced commits to gh-pages at zhangyiss/toml11 from mirror 2025-12-03 01:08:13 +08:00
46ba66edc3 feat: change some unreleased features as ext
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-12-02 15:28:15 +08:00
6c5785bc2f use thread local cpature mode (#2850)
8879ee00eb Support more Numpy interfaces for masked_scatter (#2832)
Compare 2 commits »
zhangyiss synced new reference pre-commit-ci-update-config to zhangyiss/the-littlest-jupyterhub from mirror 2025-12-02 08:58:10 +08:00
zhangyiss synced commits to pre-commit-ci-update-config at zhangyiss/the-littlest-jupyterhub from mirror 2025-12-02 08:58:10 +08:00
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-12-02 07:08:09 +08:00
6e762fe2e2 [CUDA] Migrate conv code to new cuDNN APIs (#2847)
zhangyiss synced new reference dependabot/github_actions/actions/checkout-6 to zhangyiss/the-littlest-jupyterhub from mirror 2025-12-01 16:28:10 +08:00
zhangyiss synced commits to dependabot/github_actions/actions/checkout-6 at zhangyiss/the-littlest-jupyterhub from mirror 2025-12-01 16:28:10 +08:00
zhangyiss pushed to main at zhangyiss/scixx_data 2025-11-28 10:09:36 +08:00
zhangyiss pushed to main at zhangyiss/stt 2025-11-27 15:06:08 +08:00
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-11-27 11:38:11 +08:00
2b95d0c270 [CUDA] Use cuDNN attention when T_q != T_kv (#2843)
b054838780 Added clarification to apply_fn parameter of apply_to_modules (#2831)
dd79d3c465 [CUDA] Faster rms norm for small dimension (#2838)
Compare 3 commits »
zhangyiss pushed to main at zhangyiss/scixx_data 2025-11-27 09:40:59 +08:00
c0d3ca3e00 update
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-11-26 10:58:09 +08:00
704fd1ae28 [CUDA] Support array mask in SDPA (#2822)
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-11-26 02:38:17 +08:00
c9f4dc851f Merge build-cuda and build-linux actions (#2783)
zhangyiss synced commits to main at zhangyiss/FTXUI from mirror 2025-11-25 20:12:26 +08:00
e986b98faf Add new translations.
zhangyiss synced commits to gh-pages at zhangyiss/FTXUI from mirror 2025-11-25 20:12:26 +08:00
zhangyiss synced new reference test/fix-cuda-12-9 to zhangyiss/mlx from mirror 2025-11-25 18:28:19 +08:00
zhangyiss synced commits to test/fix-cuda-12-9 at zhangyiss/mlx from mirror 2025-11-25 18:28:19 +08:00
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-11-25 18:28:10 +08:00
f8bd675655 [CUDA] Output of SDPA should have same layout with inputs (#2826)
23a9168d34 [CUDA] Add debug env to save cuda graphs to dot files (#2825)
bca205e287 [CUDA] Exit on crash and more helpful errors (#2830)
Compare 3 commits »