Commit Graph
570 Commits
Author SHA1 Message Date
XOR-op bee1a5af98 [feat] Hooks API and layerwise offloading for all DiTs (#1006) 2026-01-22 12:09:55 +00:00
William Lin 5ec0e0947c [chore] release fastvideo-kernel 0.2.3 (#1018) 2026-01-22 12:09:55 +00:00
alexzms 0224ea9a14 [Bug Fix] Add autograd wrapper for block-sparse attention in fastvideo-kernel + fix CMake extension linking (#1015) 2026-01-22 12:09:55 +00:00
William Lin f78843ca3f [CI] Fix OOM issues in ssim tests (#1011) 2026-01-22 12:09:50 +00:00
alexzmsandWill Lin 8c9940713a [CI] SSIM tests optimization: load all model weights from Modal persistent Volume (#958)
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2026-01-22 12:09:05 +00:00
KyleShao ae439b1290 [feat] Introduce Cosmos 2.5 Text2World pipeline (#974) 2026-01-22 12:09:04 +00:00
William Lin 0d6c9a5033 [misc] [bugfix] unpin 'av' in pyproject (#1009) 2026-01-22 12:09:04 +00:00
XOR-op d8b9d7c6ab [feat!] Disable FSDP inference by default (#1001) 2026-01-22 12:09:04 +00:00
Loay Rashid 989f1d5462 [CI] Fixed Turbodiffusion I2V CI (#1002) 2026-01-22 12:09:04 +00:00
William Linandgemini-code-assist[bot] 5753d9273f [ci] temporarily disable turbodiffusion ssim test (#1000)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-22 12:09:03 +00:00
Will Lin 6b9626c0f1 Revert "dit"
This reverts commit a6a9c9ca07.
2026-01-22 12:09:03 +00:00
Will Lin c6dc7e8181 dit 2026-01-22 12:09:03 +00:00
3e4b8b278e [bugfix] Add configs for TurboDiffusion T2V/I2V models (#993)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2026-01-22 12:09:03 +00:00
Shreejith SGandWill Lin 7381e19bda [docs]: add LoRA extraction utilities documentation (#992)
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2026-01-22 12:09:03 +00:00
Shao Duan 44d32ad772 [examples] Added longcat-video python api examples (#994) 2026-01-22 12:09:03 +00:00
William Lin 6b30205e3b [chore] release 0.1.7 (real) (#980) 2026-01-22 12:09:02 +00:00
William Lin cd5c0172a5 [misc] add pin_cpu_memory false for RTX 4090 (#990) 2026-01-22 12:09:02 +00:00
Loay Rashid 490ba382b3 [feat] add Turbodiffusion I2V pipeline (#984) 2026-01-22 12:09:02 +00:00
William Lin f795892514 [misc] pin fastvideo-kernel in .toml file (#989) 2026-01-22 12:09:02 +00:00
Shao Duan ae0316971d Add LongCat-Video I2V and Video Continuation (Base, Distillation and Refinement) Support to FastVideo (#953) 2026-01-22 12:09:02 +00:00
William Lin 98452d99dc [chore] update wechat QR code (#988) 2026-01-22 12:09:01 +00:00
William Lin 9d1cb80fd2 [chore] release fastvideo-kernel 0.2.2 (#986) 2026-01-22 12:09:01 +00:00
William Lin 5dc8625d78 [ci] increase ssim and lora inference test timeout (#985) 2026-01-22 12:09:01 +00:00
William Lin 0db7e3c1e9 [docs] Update docs and README (#975) 2026-01-22 12:09:01 +00:00
Ohm-Rishabh f72ced7611 Layer offloading (#966) 2026-01-22 12:09:01 +00:00
XOR-op a6b738fe42 [feat] Support text encoder weight override and quantization (#983) 2026-01-22 12:09:01 +00:00
Kaiqin Kong ac013acff5 [feat] support Matrix-Game 2.0 streaming generation (#957) 2026-01-22 12:09:00 +00:00
Loay Rashid f74d6e7aff [New Model] Turbodiffusion (#971) 2026-01-22 12:09:00 +00:00
XOR-op b894a8224e [feat] Support absmax style quantization for FP8 (#981) 2026-01-22 12:08:56 +00:00
Qi Jia e24ea17a67 [docs]: fix various broken links across the documentation (#979) 2026-01-22 12:08:00 +00:00
William Lin 6c18dda16c [kernel] add turbodiffusion kernels (#972) 2026-01-22 12:07:55 +00:00
William Lin 1afbf8c7c8 [misc] Add util script to create diffuser HF repo from custom component weights (#970) 2026-01-22 12:06:41 +00:00
RoyWangandroywang 9c3b8acc6f [fix]: fix STA trition kernel for AMD RDNA archs (#969)
Co-authored-by: roywang <roywang@amd.com>
2026-01-22 12:06:41 +00:00
RoyWangandroywang bf1892b8a8 [fix]: fix fastvideo-kernel Rocm build and Dockerfile for Rocm (#968)
Co-authored-by: roywang <roywang@amd.com>
2026-01-22 12:06:41 +00:00
6eedc0acb0 [fix]: fix sliding_tile_attn with sdpa(without flash_attn) (#967)
Co-authored-by: roywang <roywang@amd.com>
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2026-01-22 12:06:41 +00:00
Ketaki Tank 05214b5aef [feat] Add new feature extractors for fvd (#954) 2026-01-22 12:06:40 +00:00
William Lin 9eabb5da78 [chore] release v0.1.7 (#955) 2026-01-22 12:06:40 +00:00
William Lin 1a637e7a75 [kernel] Fix docker release build for kernel (#965) 2026-01-22 12:06:40 +00:00
William Lin 9ba352fcf3 [docs] refactor attention docs (#964) 2026-01-22 12:06:40 +00:00
William Lin 042c20fd9d [kernel] Release fastvideo-kernel v0.2.1 (#963) 2026-01-22 12:06:40 +00:00
William LinandShreejithSG 254b49cdb7 [kernel] Reorg and fix fastvideo-kernel (#962)
Co-authored-by: ShreejithSG <shreejithsg@gmail.com>
2026-01-22 12:06:40 +00:00
Shreejith SGandWilliam Lin 8f4cd10b49 feat: consolidate attention kernels into unified fastvideo-kernel package (#946)
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com>
2026-01-22 12:06:39 +00:00
alexzmsandShao Duan 9211fa84fc Add LongCat T2V (Base, Distillation and Refinement) Support to FastVideo (#883)
Co-authored-by: Shao Duan <shaoxiongduan@gmail.com>
2026-01-22 12:06:39 +00:00
William Lin f2cced218d [rocm] Add rocm fastvideo docker image (#952) 2026-01-22 12:06:38 +00:00
RoyWang 2f49e50150 [feat] add sliding_tile attention triton kernel and ROCM support (#916) 2026-01-22 12:06:38 +00:00
Matthew Noto b824f9536b [docs] small fixes (#947) 2026-01-22 12:06:38 +00:00
Wei Zhou fdca8fdbaa [New Model] Hunyuan1.5 (#943) 2026-01-22 12:06:38 +00:00
William Lin 6c4cb78192 [misc] Allow manual override of Pipeline class through override_pipeline_cls_name (#945) 2026-01-22 12:06:38 +00:00
Loay Rashid 2b8c937abe [bugfix] Added VSA Padding logic (#944) 2026-01-22 12:06:37 +00:00
Kaiqin Kong bdbf327aa5 [feat] Add Matrix-Game 2.0 (#938) 2026-01-22 12:06:37 +00:00