fan2956 783086bcbf [PERF] Wan2.2 support RMSNorm NPU (#2576) ...

Signed-off-by: fan2956 <zhoufan53@huawei.com>

2026-04-18 15:46:37 +08:00

..

attention

[cherry-pick][Perf] Skip Wan2.2 cross attn Ulysses SP (#2459) (#2537)

2026-04-07 10:57:02 +08:00

cache

[Cherry-pick][v0.18.0.post1][PERF] Wan2.2 support adalayernorm on NPU (#2575)

2026-04-16 08:47:38 +08:00

distributed

[cherry-pick][release/v0.18.0post1][Perf] Wan2.2 I2V optimization: convert datatype from FP32 to BF16 in… (#2618)

2026-04-09 09:57:14 +08:00

executor

[Refactor] Unify torch profiler for omni and diffusion models (#2099)

2026-03-24 15:25:52 +08:00

hooks

[Feature] support sp for hunyuan (#2163)

2026-03-27 17:28:13 +08:00

layers

[PERF] Wan2.2 support RMSNorm NPU (#2576)

2026-04-18 15:46:37 +08:00

lora

[BugFix] Fix Max Rank Handling in LoRA (#1397)

2026-03-14 02:42:54 +00:00

model_loader

[Core] Unified quantization framework (#1764)

2026-03-24 18:56:55 +08:00

models

[PERF] Wan2.2 support RMSNorm NPU (#2576)

2026-04-18 15:46:37 +08:00

offloader

[Bugfix] Maintain model-level CPU offload in a blocking way (#1978)

2026-03-26 02:08:13 +00:00

postprocess

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

profiler

[Feature] support sp for hunyuan (#2163)

2026-03-27 17:28:13 +08:00

sched

[Refactor] Refactor Diffusion Scheduler/Executor Boundaries and Request State Flow (#1625)

2026-03-23 20:25:32 +08:00

utils

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

worker

[Refactor] Unify torch profiler for omni and diffusion models (#2099)

2026-03-24 15:25:52 +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

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

diffusion_engine.py

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

envs.py

[Frontend] Rewrite video API for async job lifecycle (#1665)

2026-03-13 17:11:06 +08:00

forward_context.py

[Feature]: add Ulysses advanced_uaa mode (#1379)

2026-03-24 14:55:54 +08:00

inline_stage_diffusion_client.py

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

ipc.py

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00

registry.py

[model] support FLUX.1-Kontext-dev (#561)

2026-03-23 17:17:58 +00:00

request.py

[Bug Fix] Resolve broken image issue when TP is enabled and no seed is provided. (#2176)

2026-03-26 16:56:46 +00:00

stage_diffusion_client.py

[cherry-pick releasev0.18.0post1] Codex/release v0.18.0.post1 cherry-pick #2735/#2736/#2555 (#2813)

2026-04-17 15:44:45 +08:00