Hongsheng Liu 284e05c88b [Core] Support online FP8 with DLO AllGather (#6279) ...

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-08-18 23:48:07 +08:00

..

attention_backends

[Docs] Split diffusion attention and CPU offload guides (#6075)

2026-08-15 14:41:09 +08:00

cache_acceleration

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

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

offloader

[Core] Support online FP8 with DLO AllGather (#6279)

2026-08-18 23:48:07 +08:00

parallelism

[Bugfix] Fix HSDP compatibility with the new online FP8 linear method (#5677)

2026-08-14 15:45:55 +08:00

attention_backends.md

[Docs] Split diffusion attention and CPU offload guides (#6075)

2026-08-15 14:41:09 +08:00

cpu_offload.md

[Docs] Split diffusion attention and CPU offload guides (#6075)

2026-08-15 14:41:09 +08:00

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

[Feature]: Adds distilled LoRA support for diffusion models (#2783)

2026-08-11 14:23:43 +00:00

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

startup_and_loading.md

docs: align User Guide feature taxonomy (#6045)

2026-08-12 00:20:56 +08:00