QianCyrusandHongsheng Liu 8ef77be66e [Model] Avoid repeated attention and MLP work in Klein TP (#8553) ...

Signed-off-by: QianCyrus <101633534+QianCyrus@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-10-07 21:21:05 +08:00

..

test_flux2_klein_local_tp.py

[Model] Avoid repeated attention and MLP work in Klein TP (#8553)

2026-10-07 21:21:05 +08:00

test_flux2_klein_num_inference_steps.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

test_flux2_klein_validation.py

[Bugfix] Reject empty prompts in Flux2 Klein diffusion pipeline (#3711)

2026-05-19 11:30:54 +08:00

test_flux2_quantization.py

[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

2026-10-05 14:11:01 +08:00

test_flux2_transformer_tp.py

[Refactor][Diffusion] Complete generic backend plan consumption (#7313)

2026-09-15 08:40:04 +08:00

test_pipeline_flux2_quantization.py

[Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO (#5910)

2026-08-15 23:01:26 +08:00