vllm-omni

attention

[CI][XPU]Fix sage_attn hard-code import for cuda (#3994 )

2026-05-30 09:43:14 +08:00

batching

[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556 )

2026-05-08 14:12:23 +08:00

cache

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527 )

2026-06-20 08:30:44 +08:00

diffusion_backend

[Diffusion] Unify diffusion request identity on request_id (#3744 )

2026-05-28 14:56:56 +08:00

distributed

[Diffusion] Support USP and VAE patch parallel for HunyuanVideo 1.5 (#3979 )

2026-05-30 14:40:42 +08:00

hooks

[Bugfix] Fix Incompatible Multihook Integration (TeaCache <-> CPU Offload) (#2689 )

2026-04-12 21:44:06 +08:00

kernels/mot

[Enhancement] Introduce High-Performance MoT (Mixture-of-Tokens) Kernels: Triton Implementation (#3960 )

2026-06-16 03:08:02 +00:00

layers

[Rebase] Rebase to vllm 0.23.0 (#4286 )

2026-06-13 16:43:02 +00:00

lora

[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556 )

2026-05-08 14:12:23 +08:00

model_loader

[Core] Cleanup DiffusersPipelineLoader (#1932 )

2026-06-09 11:55:32 +08:00

models

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527 )

2026-06-20 08:30:44 +08:00

offloader

[CI] skip ci for issue 4537 (#4538 )

2026-06-18 17:53:34 +08:00

quantization

[Bugfix] Fix HSDP + FP8 online quantization compatibility (#4494 )

2026-06-19 15:06:27 +08:00

test_compile.py

[Perf]Enable regional compile for Cosmos3 HSDP blocks (#4485 )

2026-06-18 16:54:05 +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_diffusion_engine_cleanup.py

[Diffusion] Unify diffusion request identity on request_id (#3744 )

2026-05-28 14:56:56 +08:00

test_diffusion_engine_dummy_run.py

[Refactor] Extract diffusion output formatting boundary (#4407 )

2026-06-15 22:50:50 +08:00

test_diffusion_engine_metrics.py

[Refactor] Extract diffusion output formatting boundary (#4407 )

2026-06-15 22:50:50 +08:00

test_diffusion_engine_rpc_routing.py

[Diffusion] Unify diffusion request identity on request_id (#3744 )

2026-05-28 14:56:56 +08:00

test_diffusion_engine.py

Add Cosmos3 model support (#3454 )

2026-06-02 04:04:31 +08:00

test_diffusion_ipc.py

[Bugfix] Surface all-rank diffusion RPC failures (#4403 )

2026-06-13 15:42:16 +08:00

test_diffusion_model_runner.py

[Rebase] Rebase to vllm releases/v0.22.0 (#3891 )

2026-06-01 11:08:12 +08:00

test_diffusion_output_formatter.py

[Refactor] Extract diffusion output formatting boundary (#4407 )

2026-06-15 22:50:50 +08:00

test_diffusion_plugin_hooks.py

Support DROID policy server for Cosmos3 OpenPI (#4282 )

2026-06-15 21:22:59 +08:00

test_diffusion_request.py

[Diffusion] Unify diffusion request identity on request_id (#3744 )

2026-05-28 14:56:56 +08:00

test_diffusion_scheduler.py

[Refactor] Extract diffusion output formatting boundary (#4407 )

2026-06-15 22:50:50 +08:00

test_diffusion_step_pipeline.py

[Feature] Add HunyuanImage3 DiT grouped step batching (#4041 )

2026-06-15 20:36:41 +08:00

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.py

[ROCm] [CI] Fix diffusion test (#4574 )

2026-06-20 08:31:39 +08:00

test_inline_stage_diffusion_client.py

[Bugfix] Support diffusion worker dead detect when use inline engine (#3214 )

2026-05-16 20:50:29 +08:00

test_input_batch_txt_seq_lens.py

[BugFix][Qwen-Image] align txt_seq_lens RoPE width with padded embeds (#4474 )

2026-06-16 19:09:25 +08:00

test_multiproc_engine_concurrency.py

[Refactor] Omni Stage Runtime and Distributed Replica Control Plane (#3855 )

2026-06-17 14:13:20 +08:00

test_omni_diffusion_config_master_port.py

[ROCm] [CI] Bugfix Existing CI cases (#3946 )

2026-06-01 22:02:15 +08:00

test_stage_diffusion_proc.py

[Rebase] Rebase to vllm releases/v0.22.0 (#3891 )

2026-06-01 11:08:12 +08:00

test_worker_wrapper_base.py

[Core] Cleanup DiffusersPipelineLoader (#1932 )

2026-06-09 11:55:32 +08:00