ooooooye 740f45abcd [Perf][Diffusion] MiniMax-H3: opt into packed varlen attention on NPU to eliminate quadratic mask materialization (#5891) ...

Signed-off-by: brandneway <gyuan4892@gmail.com>

2026-08-10 19:47:03 +08:00

..

__init__.py

[Model] Add MiniMax H3 diffusion support (#5691)

2026-08-03 14:10:40 +08:00

test_minimax_h3_contract.py

[Perf][Diffusion] MiniMax-H3: opt into packed varlen attention on NPU to eliminate quadratic mask materialization (#5891)

2026-08-10 19:47:03 +08:00

test_minimax_h3_e2e.py

[MiniMax-H3] TeaCache support and Cache-DiT validation (#5840)

2026-08-09 15:07:21 +00:00

test_minimax_h3_packing.py

[Feature] Align MiniMax H3 official input matrix (#5752)

2026-08-05 07:12:01 +00:00

test_minimax_h3_parallel.py

[Perf][MUSA] Restore MiniMax-H3 dynamic RoPE fusion (#5881)

2026-08-10 17:24:46 +08:00

test_minimax_h3_quality_policy.py

[Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853)

2026-08-07 09:07:23 +00:00

test_minimax_h3_quantization_quality.py

[CI][Bugfix] Fix Minimax-H3 FP8 Accuracy Test (#5829)

2026-08-06 03:27:01 +00:00

test_minimax_h3_quantization.py

[Model][Feat] MiniMax H3 online FP8 support (#5737)

2026-08-04 11:35:01 +00:00