New Models Supported

LongCat-Image, LongCat-Image-Edit, Z-Image-Turbo-ControlNet, Z-Image-Turbo Nunchaku, Qwen-Image-Edit-2511, Qwen-Image-Layered

What's Changed

• Simplify CLI: Make task argument optional by @BBuf in #600
• chore: fix extra path compare by @DefTruth in #603
• CI: Add build_wheel CI by @DefTruth in #604
• feat: support cache for LongCat-Image by @e1ijah1 in #602
• feat: Serving support LORA by @BBuf in #601
• CI: Add Forward Pattern CPU CI Tests by @DefTruth in #605
• chore: Update README.md by @DefTruth in #606
• Fix typo by @BBuf in #607
• feat: z-image-controlnet 🔥4x speedup! by @DefTruth in #608
• fix lora path mismatch in examples by @DefTruth in #609
• feat: support TP and CP for longcat-image by @DefTruth in #610
• misc: fix typo by @DefTruth in #612
• feat: support 🔥Qwen-Image-Edit-2511 by @DefTruth in #614
• feat: support 🔥Qwen-Image-Layered by @DefTruth in #615
• chore: simplify parallelism dispatch by @DefTruth in #616
• chore: simplify quantize dispatch by @DefTruth in #617
• chore: refactor kernels module by @DefTruth in #618
• ci: add refresh context ci tests by @DefTruth in #619
• misc: add device info to example summary by @DefTruth in #621
• feat: support ⚡️Z-Image-Turbo Nunchaku by @DefTruth in #623
• [chore] Improve error_logging in serving tp_worker.py by @BBuf in #627
• chore: support more alias for quant types by @DefTruth in #628
• chore: fix alias rev map for quant types by @DefTruth in #629
• chore: lazy import check for quantize api by @DefTruth in #630
• chore: add more compile flags setting by @DefTruth in #631
• [Bug] Apply --attn backend in single-GPU examples by @BBuf in #633
• Bump up to v1.1.10 by @DefTruth in #634

New Contributors

• @e1ijah1 made their first contribution in #602

Full Changelog: v1.1.9...v1.1.10

What's Changed

• feat: uaa avoid extra memory IO access by @triple-mu in #551
• chore: simplify quantize flags in example utils by @DefTruth in #553
• chore: fix quantize flags in example by @DefTruth in #554
• chore: fix quantize & TP conflicts for wan by @DefTruth in #556
• feat: support serving text2video by @BBuf in #555
• chore: Update SERVING Doc and FAQ Doc by @BBuf in #557
• chore: qwen edit lightning cp/tp examples by @DefTruth in #559
• feat: support ovis-image context parallel by @DefTruth in #560
• feat: serving support image2video by @BBuf in #558
• chore: add collect_env script by @DefTruth in #562
• Add pre-commit and GitHub Actions CI by @DefTruth in #564
• chore: refactor parallelism for better reusability by @DefTruth in #565
• chore: Update vLLM-Omni integration by @SamitHuang in #566
• feat: add pipe quant config for serving by @nono-Sang in #563
• News: 🔥vLLM-Omni x Cache-DiT ready! by @DefTruth in #567
• feat: enable custom attn backend for TP by @DefTruth in #568
• feat: support TP for many text encoder by @DefTruth in #569
• fix qwen-edit-lightning examples by @DefTruth in #571
• fix get_text_encoder_from_pipe by @DefTruth in #572
• fix: handle general compile options in example utils by @DefTruth in #573
• chore: reduce un-popular examples by @DefTruth in #574
• feat: add text_encoder tp for serving by @nono-Sang in #570
• chore: simplify example by @DefTruth in #575
• chore: make unified examples by @DefTruth in #576
• chore: fix vllm-omni docs link by @DefTruth in #577
• chore: optimize examples default path mapping by @DefTruth in #579
• chore: fix vllm-omni docs link by @DefTruth in #580
• feat: support Ovis-Image tensor parallel by @DefTruth in #582
• chore: fix typo in User_Guide.md by @DefTruth in #583
• chore: fail fast TP validation for attn heads by @CPFLAME in #581
• fix patch functor for multi transformers by @DefTruth in #586
• chore: add qwen image controlnet example by @DefTruth in #588
• chore: update docs by @DefTruth in #590
• feat: register fa3 backend for context parallel by @nono-Sang in #589
• chore: support separate quant-type for text encoder by @DefTruth in #591
• hotfix for fa3 backend import error by @DefTruth in #593
• chore: fix typo in README.md by @DefTruth in #594
• chore: set save_ctx to False for inference by @nono-Sang in #596
• fix flux examples model path mismatch by @DefTruth in #597

New Contributors

• @SamitHuang made their first contribution in #566
• @nono-Sang made their first contribution in #563
• @CPFLAME made their first contribution in #581

Full Changelog: v1.1.8...v1.1.9

What's Changed

• Add request queue to limit concurrent generation requests by @BBuf in #535
• News: 🔥🔥SGLang Diffusion x Cache-DiT ready!🔥🔥 by @DefTruth in #536
• feat: optimize async fp8 ulysses attn by @DefTruth in #537
• chore: delete useless code in serving by @BBuf in #539
• feat: make all_to_all comm unified by @DefTruth in #538
• feat: add refresh cache context api by @DefTruth in #542
• feat: support image edit model in serving by @BBuf in #541
• chore: simplify ulysses async flag by @DefTruth in #543
• chore: re-registered sage attn backend by @DefTruth in #544
• feat: support any head num for ulysses by @DefTruth in #546
• feat: support uneven heads in ulysses w/o padding by @triple-mu in #547
• chore: refactor FLUX.2 image editing tests by @BBuf in #548
• feat: Add ulysses for any heads w/o padding by @DefTruth in #549
• feat: add envs manager for cache-dit by @DefTruth in #550
• fix ulysses fp8 and uneven head conflicts by @DefTruth in #552

Full Changelog: v1.1.7...v1.1.8

hotfix for diffusers 0.35.2 compatible

What's Changed

• feat: pointer casting for fp8 all2all by @triple-mu in #533
• chore: relax block adapter deps by @DefTruth in #534

Full Changelog: v1.1.6...v1.1.7

hotfix for diffusers 0.35.2 compatible

What's Changed

• Add heartbeat to avoid nccl timeout when the service hangs. by @BBuf in #531
• chore: remove un-needed cp imports by @DefTruth in #532

Full Changelog: v1.1.5...v1.1.6

What's Changed

• Add profiler for flux tp and cp example by @BBuf in #501
• chore: Update README.md by @DefTruth in #502
• feat: support FnB0 for z-image w/ cp by @DefTruth in #503
• feat: support _sdpa_cudnn backend for cp by @DefTruth in #504
• feat: support async ulysses cp for z-image by @DefTruth in #505
• feat: add all_to_all_single v2 by @DefTruth in #507
• feat: support async ulysses cp for qwen-image by @DefTruth in #508
• feat: support all2all qkv per token fp8 by @triple-mu in #509
• chore: improve flux2 and qwen image examples by @BBuf in #512
• fix: workaround for uaa-fp8 .view compile error by @triple-mu in #514
• feat: relaxed transformer strict assert by @DefTruth in #515
• feat: all2all qkv fp8 for ulysses by @DefTruth in #516
• feat: support pre-defined step masks by @DefTruth in #517
• chore: separate chrono-edit and wan cp plan by @DefTruth in #519
• fix example utils.py uaa fp8 flag typo by @DefTruth in #521
• feat: extend predefined step masks for 4/6 steps by @DefTruth in #523
• misc: add z-image-turbo predefined step masks by @DefTruth in #525
• feat: support per_token_quant_fp8 triton kernel by @triple-mu in #524
• feat: unified async ulysses fp8 by @DefTruth in #526
• feat: support serving for cache-dit by @BBuf in #522
• Fix get_model_info api 404 when serving with tp/cp by @BBuf in #529
• feat: support cache for hunyuanvideo-1.5 by @DefTruth in #528
• feat: support cache for ovis-image by @DefTruth in #530

New Contributors

• @triple-mu made their first contribution in #509

Full Changelog: v1.1.4...v1.1.5

What's Changed

• feat: support torch profiler in cache-dit by @BBuf in #491
• feat: support 🔥z-image tensor parallel by @gameofdimension in #494
• feat: support lumina2 tensor parallel by @gameofdimension in #495
• feat: support cache for 🔥z-image by @DefTruth in #496
• feat: support context parallel for 🔥z-image by @DefTruth in #497
• fix: temp FnB(n>0) workaround for z-image cache w/ cp by @DefTruth in #499

Full Changelog: v1.1.3...v1.1.4

What's Changed

• chore: Add wan 2.2 i2v context parallel example by @DefTruth in #476
• chore: optimize wan examples, compile & offload by @BBuf in #477
• feat: support async ulysses cp for flux by @DefTruth in #480
• chore: update support matrix by @DefTruth in #484
• chore: update async ulysses cp docs by @DefTruth in #486
• chore: update async ulysses cp refs by @DefTruth in #487
• feat: support FLUX.2-dev Tensor Parallelism by @gameofdimension in #485
• feat: support Hybrid cache + TP for 🔥FLUX.2 by @DefTruth in #489
• feat: Add seq offload for 🔥FLUX.2 w/o parallel by @DefTruth in #490
• feat: support 🔥FLUX.2 context parallel by @DefTruth in #492

Full Changelog: v1.1.2...v1.1.3

What's Changed

• chore: Update README.md by @DefTruth in #455
• fix load options drop kwargs by @DefTruth in #456
• chore: add maybe pad prompt utils by @DefTruth in #458
• fix: move .to(device) to reduce tp mem by @BBuf in #459
• example: support more overrided args and memory tracker by @BBuf in #461
• Add missing model-path args in example by @BBuf in #463
• UAA: ulysses anything attn w/ zero overhead by @DefTruth in #462
• fix qwen-image multi-gpu mismatch by @BBuf in #464
• Fix more models multi gpu mismatch by @BBuf in #466
• feat: support unshard anything for UAA by @DefTruth in #465
• chore: update qwen-image example for UAA by @DefTruth in #468
• chore: Update README.md by @DefTruth in #470
• chore: Update README.md by @DefTruth in #471
• support skyreels cp and tp ulysses by @BBuf in #469
• always use vae tiling if vram <= 48 GiB for qwen-image by @DefTruth in #472
• chore: Add SkyReelsV2 tp/cp to support-matrix by @BBuf in #473
• fix: correct string literal syntax errors in examples by @BBuf in #475
• feat: allow UAA in compiled graph by @DefTruth in #474

New Contributors

• @BBuf made their first contribution in #459

Full Changelog: v1.1.1...v1.1.2

What's Changed

• chore: Update README.md by @DefTruth in #442
• feat: support step compute mask by @DefTruth in #444
• bugfix: fix bench distill cfg mismatch by @DefTruth in #445
• chore: update step mask docs by @DefTruth in #446
• chore: Update User_Guide.md by @DefTruth in #447
• chore: update README by @DefTruth in #448
• chore: update step mask example by @DefTruth in #449
• chore: hightlight SCM - step computation mask by @DefTruth in #450
• chore: hightlight SCM - step computation mask by @DefTruth in #451
• chore: hightlight SCM - step computation mask by @DefTruth in #452
• misc: support quantize and attn backend for flux example by @DefTruth in #453
• misc: add quant and attn backend -> step mask example by @DefTruth in #454

Full Changelog: v1.1.0...v1.1.1