Anjie HouandHongsheng Liu 8a49c65bf9 [Core][Diffusion] Add byte backpressure to chunk transfers (#7916) ...

Signed-off-by: specture724 <specture724@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-09-26 17:48:32 +08:00

..

__init__.py

[Diffusion] Qwen image support (#82)

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

chunked_video.py

[Core][Diffusion] Add byte backpressure to chunk transfers (#7916)

2026-09-26 17:48:32 +08:00

flow_matching.py

[BugFix][Diffusion] Add CPU LAPACK fallback for FlowUniPC (#5329)

2026-07-30 15:09:48 +00:00

future_utils.py

[Bugfix][Diffusion] Drop aborted request's orphaned async output (fix #6413) (#6439)

2026-09-23 16:58:46 +00:00

hf_utils.py

[Model] Add native MAGI-2 Preview diffusion support (#5918)

2026-09-05 15:32:30 +08:00

image_output.py

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

kv_utils.py

[Feature] Add AllGather-KV sequence-parallel attention str… (#4968)

2026-07-24 14:45:26 +00:00

media_utils.py

[5/N] Schedule chunk transfers as their own stage (#7406)

2026-09-18 09:27:56 +08:00

network_utils.py

[Diffusion] Qwen image support (#82)

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

param_utils.py

[Refactor]Base class for dit pipelines with unified parameter declaration[1/N] (#4225)

2026-06-18 17:14:18 +08:00

prompt_utils.py

[Bugfix] enforce max_sequence_length for Qwen-Image and Wan2.2 series before encoding (#2847)

2026-04-17 10:40:36 +08:00

size_utils.py

[Bugfix] Fix Qwen-Image min-size normalization for tiny requests (#2637)

2026-04-09 20:51:01 +08:00

tf_utils.py

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

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

video_decode.py

[BugFix][Cosmos3] Decode uploaded video paths in v2v preprocess (#8106)

2026-09-25 07:53:24 +00:00