JohnJanandJiangyun Zhu 8135ee81e6 [feature]: support flux cache_dit (#1145) ...

Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-02-04 22:10:04 +08:00

..

attention

[CI] Refactor test_sequence_parallel.py and add a warmup run for more accurate performance stat (#1165)

2026-02-03 12:23:15 +08:00

cache

[feature]: support flux cache_dit (#1145)

2026-02-04 22:10:04 +08:00

distributed

[Bugfix] Fix tp+sp accuracy, incorrect process group mapping (#1178)

2026-02-04 16:54:47 +08:00

executor

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

hooks

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

layers

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

lora

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

model_loader

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

models

[Perf] resolving prolonged cudastreamsynchronize execution in z image processing (#1105)

2026-02-04 10:35:28 +08:00

profiler

[Core] Implement Diffusion Profiler Support (#709)

2026-01-20 11:35:48 +08:00

utils

[Bugfix] Fix generation artifacts of Qwen-Image-Edit-2511 and update pipeline DiT param parsing (#776)

2026-01-15 11:18:28 +08:00

worker

[Platform] Add supports_torch_inductor interface (#1108)

2026-01-30 15:21:43 +00:00

__init__.py

[Diffusion] Qwen image support (#82)

2025-11-28 14:22:11 +08:00

compile.py

[core] add torch compile for diffusion (#684)

2026-01-09 04:05:44 +13:00

data.py

[Perf]: CFG parallel abstraction (#851)

2026-01-30 16:23:44 +00:00

diffusion_engine.py

[Debug] Correct Unreasonable Long Timeout (#1175)

2026-02-03 08:49:51 +00:00

envs.py

[Diffusion][Bugfix] Fix the flash_attn backends selection logic (#983)

2026-01-29 16:44:58 +08:00

forward_context.py

[Diffusion] Non-Intrusive Sequence Parallelism (SP) Model Support Abstraction for vLLM-Omni Framework (#779)

2026-01-21 14:43:09 +08:00

offload.py

[Feature] Support DiT Layerwise (Blockwise) CPU Offloading (#858)

2026-01-30 17:35:09 +08:00

registry.py

[Model]: add FLUX.1-dev model (#853)

2026-01-28 16:28:57 +08:00

request.py

[Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797)

2026-01-28 16:07:42 +08:00

scheduler.py

[chore] Remove zmq context initialize (#1187)

2026-02-04 06:34:15 +00:00