Zijun HuangandWeiQing Chen 93457f29ff [NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706) ...

Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>

2026-08-06 14:15:21 +08:00

..

cache_acceleration

Codex revert pr reviewer (#2959)

2026-04-21 21:43:15 +08:00

parallelism

[Feature] Spatially-sharded (SP) decode for the Wan VAE (#4620)

2026-06-27 09:01:25 +08:00

attention_backends.md

[NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706)

2026-08-06 14:15:21 +08:00

cpu_offload_diffusion.md

[Feature] Distributed layerwise offload with DP multi-concurrency + mmap weight… (#5397)

2026-07-30 13:35:38 +00:00

execution_modes.md

[docs] consolidate diffusion execution modes (#5599)

2026-08-05 22:41:18 +08:00

frame_interpolation.md

[REFACT]Refactor diffusion outputs to payload metadata (#4922)

2026-07-14 17:24:03 +08:00

lora.md

[Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134)

2026-04-13 14:20:04 +08:00

mot_config.md

[Enhancement] Introduce High-Performance MoT (Mixture-of-Tokens) Kernels: Triton Implementation (#3960)

2026-06-16 03:08:02 +00:00

regional_compilation.md

[perf] Add configurable diffusion compile granularity (#4603)

2026-07-24 15:22:06 +00:00