张壹 zhangyiss
  • Joined on 2024-09-10
zhangyiss synced commits to macros-to-templates at zhangyiss/mlx from mirror 2025-06-29 21:11:16 +08:00
zhangyiss synced new reference macros-to-templates to zhangyiss/mlx from mirror 2025-06-29 21:11:16 +08:00
zhangyiss synced commits to refs/pull/2290/merge at zhangyiss/mlx from mirror 2025-06-29 21:11:16 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 3 commits »
zhangyiss pushed to main at zhangyiss/stt 2025-06-29 14:08:24 +08:00
f2d36a1f85 update to v1.4.1
zhangyiss synced commits to refs/pull/2297/merge at zhangyiss/mlx from mirror 2025-06-29 13:01:14 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2219/merge at zhangyiss/mlx from mirror 2025-06-29 04:51:14 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
656ed7f780 Fix get 2d grid dims (#2316)
Compare 4 commits »
zhangyiss synced commits to refs/pull/2234/merge at zhangyiss/mlx from mirror 2025-06-28 12:13:22 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
Compare 2 commits »
zhangyiss synced commits to refs/pull/2294/merge at zhangyiss/mlx from mirror 2025-06-28 12:13:22 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2300/merge at zhangyiss/mlx from mirror 2025-06-28 12:13:22 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2317/head at zhangyiss/mlx from mirror 2025-06-28 12:13:22 +08:00
770f57e4e5 format
c1cd7bf210 cache graph
3065394ef1 use kernels in unary
e1e959da21 fix bug
2357edfec0 use node api directly to reduce overhead
Compare 19 commits »
zhangyiss synced commits to refs/pull/2317/merge at zhangyiss/mlx from mirror 2025-06-28 12:13:22 +08:00
420f0d1b8f Merge 770f57e4e5bbfe5ef00b60e7d180e6fc7ef22afb into 772f471ff2
770f57e4e5 format
c1cd7bf210 cache graph
3065394ef1 use kernels in unary
e1e959da21 fix bug
Compare 17 commits »
zhangyiss synced and deleted reference refs/tags/cuda-reduce at zhangyiss/mlx from mirror 2025-06-28 12:13:21 +08:00
zhangyiss synced and deleted reference refs/tags/refs/pull/2314/merge at zhangyiss/mlx from mirror 2025-06-28 12:13:21 +08:00
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-06-28 12:13:21 +08:00
772f471ff2 [CUDA] Fix reductions (#2314)
zhangyiss synced commits to refs/pull/2234/merge at zhangyiss/mlx from mirror 2025-06-27 19:31:17 +08:00
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 2 commits »
zhangyiss synced commits to refs/pull/2314/head at zhangyiss/mlx from mirror 2025-06-27 19:31:17 +08:00
bc60a31cae Comments
zhangyiss synced commits to refs/pull/2314/merge at zhangyiss/mlx from mirror 2025-06-27 19:31:17 +08:00
bc60a31cae Comments
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2317/merge at zhangyiss/mlx from mirror 2025-06-27 19:31:17 +08:00
ea914b8471 Merge 311d04fbd570992f697879b49409eada906f9e6d into 2c11d10f8d
2c11d10f8d Split broadcast so it is always fused in compile (#2318)
Compare 2 commits »
zhangyiss synced commits to cuda-reduce at zhangyiss/mlx from mirror 2025-06-27 19:31:16 +08:00
bc60a31cae Comments
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-06-27 19:31:16 +08:00
2c11d10f8d Split broadcast so it is always fused in compile (#2318)