nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[perf] Cache MLX H3 text refinement and speed up attention (#2002)

Browse Source 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
This commit is contained in:
posiposi443-ops
2026-10-23 12:40:47 -07:00
committed by GitHub
co-authored by Aryan Kumar
parent 1a1e7216d2
commit 8db2d71ef2
17 changed files with 1382 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/ci-macos-mlx.yml
+6
View File
@@ -88,7 +88,10 @@ jobs:
fastvideo/tests/mlx/test_mlx_affine_dq_gemm.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_parity.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_sdpa.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_nax.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_regressions.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_prefix_kv.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_fast_mode.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_fast_spatial.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_ref_layout.py \
@@ -160,7 +163,10 @@ jobs:
fastvideo/tests/mlx/test_mlx_affine_dq_gemm.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_parity.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_sdpa.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_nax.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_vsa_regressions.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_prefix_kv.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_fast_mode.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_fast_spatial.py \
fastvideo/tests/mlx/test_mlx_minimax_h3_ref_layout.py \