vllm-omni/tests/diffusion at 0c82bb1315d186ff9b5126679517b16d819b298e - vllm-omni - Gitea: Git with a cup of tea

anodyine/vllm-omni

0 Fork 0

Files

T

History

Isotr0py 0c82bb1315 Gate persistent DiT staging on decode-graph models

ModelLevelOffloadBackend passed persistent_dit_staging=(device is CUDA) for
every model, so Qwen-Image 2.0/FLUX/WAN-style sequential offload kept DiT
device storage alive across swaps instead of freeing VRAM. Only retain
staging when a DiT actually captures weight pointers (enable_cuda_graph_decode);
other models keep plain move semantics. Add tests pinning both behaviors.

2026-09-22 08:58:32 +00:00

..

[LingBot World] Eleven bit-identical removals of repeated work in the realtime path (#7648 )

2026-09-21 06:12:45 +00:00

Merge remote-tracking branch 'origin/main' into qwen-image-2.1

2026-09-22 01:23:45 +00:00

[Config] Remove diffusion_batch_size and use max_num_seqs instead. (#6484 )

2026-09-01 01:02:54 +00:00

[Model] MammothModa2: enable Cache-DiT acceleration for the DiT stage (#7291 )

2026-09-21 18:34:12 -07:00

diffusion_backend

[diffusion][feature] Add component-selective offload policies (#5929 )

2026-09-06 05:40:09 +08:00

[Feat] Add native Mooncake KV transfer from AR to DiT (#7166 )

2026-09-20 14:44:55 +00:00

Merge remote-tracking branch 'origin/main' into qwen-image-2.1

2026-09-22 01:23:45 +00:00

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951 )

2026-07-29 23:53:03 +08:00

[Refactor][Diffusion] Move single-model layers into their model directories (#5908 )

2026-09-20 18:19:24 +08:00

[Model] Add MiniMax-H3 long-video latent continuation with driving audio (#7838 )

2026-09-20 23:44:33 +08:00

[Perf][Diffusion] Activate NPU/GPU matmul for LoRA delta computation when weights are on CPU (#7590 )

2026-09-18 16:51:23 +08:00

[Bugfix] Isolate weekly CPU tests from inherited attention env and hf_api mocks (#7565 )

2026-09-21 15:55:00 +00:00

Merge branch 'main' into qwen-image-2.1

2026-09-22 10:11:12 +08:00

Gate persistent DiT staging on decode-graph models

2026-09-22 08:58:32 +00:00

[Refactor] Reject unknown diffusion config fields (#5172 )

2026-09-19 15:37:34 +00:00

[Feature][MiniMax-H3] Fuse the FastH3 four-step adapter at load time (#6714 )

2026-08-31 12:04:58 +08:00

streaming_interactive_generation

[Core][Diffusion] Camera interaction for diffusion streaming generation (LingBot World 2 as example) (#7198 )

2026-09-20 16:19:41 +00:00

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

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

conftest.py

[AMD] [CI] Fix tests for v0.28.0 (#6830 )

2026-08-31 09:10:27 +08:00

test_async_output_timeout.py

[Bugfix] Make the async-output wait bound configurable and default it higher (#6255 )

2026-08-22 22:10:30 +08:00

test_async_output_worker.py

[Core][Diffusion] Add pause_generation(mode="keep") for diffusion stages (#7685 )

2026-09-22 01:31:22 +08:00

test_attention_compile.py

[Bugfix][CI]Fix HSDP regional compile boundary (#4668 )

2026-06-25 02:52:52 +00:00

test_compile.py

fix: keep DLO hooks outside regional compilation (#6073 )

2026-08-22 21:44:03 +08:00

test_data_is_moe.py

[Model] Extend NPU support for HunyuanImage3 Diffusion Model (#1689 )

2026-03-12 20:49:17 +08:00

test_device_output_preparation.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_device_reduction.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_diffusion_config_fields.py

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951 )

2026-07-29 23:53:03 +08:00

test_diffusion_config_propagation.py

Merge remote-tracking branch 'origin/main' into qwen-image-2.1

2026-09-21 07:32:04 +00:00

test_diffusion_engine_cleanup.py

[Diffusion] Add native paged KV backend for diffusion workers (#6102 )

2026-08-22 21:45:45 +08:00

test_diffusion_engine_dummy_run.py

[Bugfix] Skip generic text-only warmup for DreamZero (#7548 )

2026-09-16 14:43:18 +08:00

test_diffusion_engine_metrics.py

[Core][Frontend] Unified Full-duplex Framework (#7413 )

2026-09-16 15:35:36 +08:00

test_diffusion_engine_rpc_routing.py

[Core][Diffusion] Add pause_generation(mode="keep") for diffusion stages (#7685 )

2026-09-22 01:31:22 +08:00

test_diffusion_engine.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

test_diffusion_ipc.py

[CI]Remove DreamID-Omni and MagiHuman support (#6357 )

2026-08-26 01:31:12 +00:00

test_diffusion_model_runner.py

[Feat] Add native Mooncake KV transfer from AR to DiT (#7166 )

2026-09-20 14:44:55 +00:00

test_diffusion_output_formatter.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

test_diffusion_output_metadata.py

[CI] Remove AudioX and MammothModa2 support (#6353 )

2026-08-23 04:22:05 +00:00

test_diffusion_plugin_hooks.py

[diffusion][bugfix] Separate Diffusers hooks from model metadata (#6749 )

2026-08-29 17:37:14 +00:00

test_diffusion_request.py

[Model] Add BAGEL step execution and continuous batching (#6359 )

2026-09-04 01:36:11 +00:00

test_diffusion_scheduler.py

[Core][Diffusion] Add pause_generation(mode="keep") for diffusion stages (#7685 )

2026-09-22 01:31:22 +08:00

test_diffusion_step_pipeline.py

[LingBot World] Eleven bit-identical removals of repeated work in the realtime path (#7648 )

2026-09-21 06:12:45 +00:00

test_diffusion_worker_broadcast.py

[Bugfix] Release GPU memory after diffusion execution failures (#6385 )

2026-08-22 18:32:48 +00:00

test_diffusion_worker_cuda_profiler.py

[Misc] Cleanup: use consistent pytest-mock in unit tests (#2698 )

2026-04-13 19:21:42 +08:00

test_diffusion_worker_process_title.py

[Core] Restore topology-aware diffusion worker titles (#6722 )

2026-08-29 08:45:57 +08:00

test_diffusion_worker_synchronize_device.py

[Core][Diffusion] Add pause_generation(mode="keep") for diffusion stages (#7685 )

2026-09-22 01:31:22 +08:00

test_diffusion_worker.py

[Bugfix][Diffusion] Fuse distilled LoRA weights before HSDP sharding (#6948 )

2026-09-06 01:29:59 +08:00

test_inductor_divisibility_patch.py

[Rebase] Rebase to vllm 0.27.0 (#5976 )

2026-08-11 15:23:46 +00:00

test_inline_stage_diffusion_client.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

test_input_batch_txt_seq_lens.py

[Refactor]: clean up diffusion scheduler interfaces (#5216 )

2026-07-22 14:05:49 +08:00

test_ipc_async.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_media_output_contract.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_multiproc_engine_concurrency.py

Merge remote-tracking branch 'origin/main' into qwen-image-2.1

2026-09-21 07:32:04 +00:00

test_omni_diffusion_config_master_port.py

[BugFix] Eliminate distributed test port race by switching to file:// rendezvous (#6468 )

2026-08-23 07:08:44 +08:00

test_omni_diffusion_config_offline_model_path.py

[Bugfix][Diffusion] Honor HF_HUB_OFFLINE in OmniDiffusionConfig (align with AR stage) (#5403 )

2026-07-30 15:07:46 +00:00

test_result_pump.py

[Bugfix] Prevent DiffusionResultPump crash on cancelled futures (#5793 ) (#5983 )

2026-08-15 16:19:45 +00:00

test_stage_diffusion_proc.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

test_uniproc_executor.py

[Core] Add UniProc diffusion executor for single-GPU (#6308 )

2026-08-22 21:58:21 +08:00

test_video_transport_defaults_are_inert.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_wan_device_reduction.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

test_worker_wrapper_base.py

[Model] Add circlestone-labs/Anima (#4083 )

2026-09-19 16:16:38 +00:00