R0CKSTAR 29b818a785 feat(magi2): add fused BF16 routed MoE path (#7206) ...

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

2026-09-28 23:20:30 +08:00

..

_magi2_gpu_bench.py

feat(magi2): add fused mHC post-processing (#7261)

2026-09-25 16:25:12 +08:00

_magi2_musa_bench.py

feat(magi2): add fused SwiGLU7 activation (#7252)

2026-09-26 22:53:04 +08:00

bench_qwen_select01_modulation.py

[Diffusion] Fuse Qwen-Image-Edit select01 modulation for CUDA (#5921)

2026-09-16 19:06:28 +08:00

benchmark_diffusion_lora_expand.py

[Core] Optimize diffusion LoRA expand accumulation (#6268)

2026-09-03 10:37:35 +08:00

benchmark_magi2_bf16_moe.py

feat(magi2): add fused BF16 routed MoE path (#7206)

2026-09-28 23:20:30 +08:00

benchmark_magi2_mhc.py

feat(magi2): add fused mHC post-processing (#7261)

2026-09-25 16:25:12 +08:00

benchmark_magi2_swiglu7.py

feat(magi2): add fused SwiGLU7 activation (#7252)

2026-09-26 22:53:04 +08:00

benchmark_ming_istft.py

[Kernel] Fuse Ming streaming ISTFT overlap-add and normalization (#7338)

2026-09-14 15:25:25 -07:00

mot_linear_benchmarks.py

[Refactor][Diffusion] Move single-model layers into their model directories (#5908)

2026-09-20 18:19:24 +08:00