张壹 zhangyiss
0 Followers · 0 Following
  • Joined on 2024-09-10
Repositories
54
 Projects Packages Public Activity Starred Repositories
zhangyiss synced and deleted reference refs/tags/custom_kernel_caching at zhangyiss/mlx from mirror 2025-06-07 11:11:15 +08:00
zhangyiss synced and deleted reference refs/tags/layernorm at zhangyiss/mlx from mirror 2025-06-07 11:11:15 +08:00
zhangyiss synced commits to refs/pull/2246/head at zhangyiss/mlx from mirror 2025-06-07 03:01:16 +08:00
97bd67c032 Check for valid launch parameters
570dd8287a Fix formatting
7734bc5c4f Change layernorms to two pass algorithm
a5ac9244c4 fix linux linking error (#2248)
Compare 4 commits »
zhangyiss synced commits to refs/pull/2246/merge at zhangyiss/mlx from mirror 2025-06-07 03:01:16 +08:00
a11f4fb460 Merge 97bd67c032 into c6a20b427a
97bd67c032 Check for valid launch parameters
c6a20b427a Improve metal elementwise kernels (#2247)
570dd8287a Fix formatting
7734bc5c4f Change layernorms to two pass algorithm
Compare 6 commits »
zhangyiss synced commits to refs/pull/2158/merge at zhangyiss/mlx from mirror 2025-06-07 03:01:15 +08:00
46eacf1276 Merge 8e3e59e6d56441a5195b9e3b758c76da56d9f322 into c6a20b427a
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2219/merge at zhangyiss/mlx from mirror 2025-06-07 03:01:15 +08:00
b2e65f02a1 Merge d2e0b0465c into c6a20b427a
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
c763fe1be0 default strict mode for module update and update_modules (#2239)
Compare 4 commits »
zhangyiss synced commits to refs/pull/2234/merge at zhangyiss/mlx from mirror 2025-06-07 03:01:15 +08:00
99ad6689e1 Merge 4d68bd3250 into c6a20b427a
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 3 commits »
zhangyiss synced commits to refs/pull/2242/head at zhangyiss/mlx from mirror 2025-06-07 03:01:15 +08:00
6741d15735 alternative solution
ac1117b224 Fix unintuitive metal kernel caching
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 4 commits »
zhangyiss synced commits to refs/pull/2242/merge at zhangyiss/mlx from mirror 2025-06-07 03:01:15 +08:00
a8480de0e0 Merge 6741d15735 into c6a20b427a
6741d15735 alternative solution
ac1117b224 Fix unintuitive metal kernel caching
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 5 commits »
zhangyiss synced and deleted reference refs/tags/metal_elementwise at zhangyiss/mlx from mirror 2025-06-07 03:01:14 +08:00
zhangyiss synced commits to custom_kernel_caching at zhangyiss/mlx from mirror 2025-06-07 03:01:14 +08:00
6741d15735 alternative solution
ac1117b224 Fix unintuitive metal kernel caching
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 4 commits »
zhangyiss synced commits to layernorm at zhangyiss/mlx from mirror 2025-06-07 03:01:14 +08:00
97bd67c032 Check for valid launch parameters
570dd8287a Fix formatting
7734bc5c4f Change layernorms to two pass algorithm
a5ac9244c4 fix linux linking error (#2248)
Compare 4 commits »
zhangyiss synced commits to main at zhangyiss/mlx from mirror 2025-06-07 03:01:14 +08:00
c6a20b427a Improve metal elementwise kernels (#2247)
a5ac9244c4 fix linux linking error (#2248)
Compare 2 commits »
zhangyiss synced new reference layernorm to zhangyiss/mlx from mirror 2025-06-06 18:51:13 +08:00
zhangyiss synced commits to refs/pull/2074/merge at zhangyiss/mlx from mirror 2025-06-06 18:51:13 +08:00
0fa9ef0757 Merge eeaf1fa463 into c763fe1be0
c763fe1be0 default strict mode for module update and update_modules (#2239)
52dc8c8cd5 Add profiler annotations in common primitives for CUDA backend (#2244)
aede70e81d Perf regression fix (#2243)
85a8beb5e4 Avoid atomic updates across CPU/GPU in CUDA event (#2231)
Compare 9 commits »
zhangyiss synced commits to refs/pull/2242/head at zhangyiss/mlx from mirror 2025-06-06 18:51:13 +08:00
d95f23940b alternative solution
896f537ff7 Fix unintuitive metal kernel caching
c763fe1be0 default strict mode for module update and update_modules (#2239)
52dc8c8cd5 Add profiler annotations in common primitives for CUDA backend (#2244)
aede70e81d Perf regression fix (#2243)
Compare 8 commits »
zhangyiss synced commits to refs/pull/2242/merge at zhangyiss/mlx from mirror 2025-06-06 18:51:13 +08:00
77a6cb6877 Merge d95f23940b6868fc1f1d72914860a7a5f780538a into c763fe1be0
d95f23940b alternative solution
896f537ff7 Fix unintuitive metal kernel caching
Compare 3 commits »
zhangyiss synced commits to custom_kernel_caching at zhangyiss/mlx from mirror 2025-06-06 18:51:12 +08:00
d95f23940b alternative solution
896f537ff7 Fix unintuitive metal kernel caching
c763fe1be0 default strict mode for module update and update_modules (#2239)
52dc8c8cd5 Add profiler annotations in common primitives for CUDA backend (#2244)
aede70e81d Perf regression fix (#2243)
Compare 8 commits »
zhangyiss synced commits to layernorm at zhangyiss/mlx from mirror 2025-06-06 18:51:12 +08:00
zhangyiss synced commits to refs/pull/900/merge at zhangyiss/FTXUI from mirror 2025-06-06 18:01:15 +08:00
eb7b7c9da5 Merge baa5973128 into 6440a88dc6
6440a88dc6 Add docs for additional install methods (#1059)
14da21b0ee Improve documentation (#1058)
a86d8f32d7 docs: fix module documentation (#1056)
3367c3a005 docs: fix typos and grammar (#1055)
Compare 9 commits »