TJian 46e96e18e3 [ROCm] [Perf] Add AITER Flash Attention (#941) ...

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>

2026-01-27 20:14:49 +08:00

..

attention

[ROCm] [Perf] Add AITER Flash Attention (#941)

2026-01-27 20:14:49 +08:00

cache

[Perf] avoid cpu op in QwenImageCrossAttention (#942)

2026-01-27 12:15:35 +08:00

distributed

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

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

executor

[Core]Add Diffusion executor (#865)

2026-01-22 05:32:44 +13:00

hooks

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

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

layers

[Model] Support Qwen-Image series models on NPU (#463)

2025-12-27 10:46:10 +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

[diffusion] add tp for FLUX.2-klein (#973)

2026-01-27 08:37:25 +00:00

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

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

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

__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

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

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

diffusion_engine.py

[Bugfix] raise error in diffusion engine and fix offload test (#933)

2026-01-25 23:04:11 +08:00

envs.py

[Diffusion]: Diffusion Ulysses-Sequence-Parallelism support (#189)

2025-12-17 15:41:31 +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] cpu offloading support for diffusion (#497)

2026-01-12 10:41:18 +00:00

registry.py

[Diffusion][Feature] Non-Intrusive Sequence Parallelism (SP) Support for Wan2.2 (#966)

2026-01-27 11:33:38 +08:00

request.py

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

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

scheduler.py

[Bugfix] raise error in diffusion engine and fix offload test (#933)

2026-01-25 23:04:11 +08:00