thu-ml/TurboDiffusion

View on GitHub

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Stars: 3.7k
Forks: 277
Open beginner issues: 0
Indexed issues: 72
Avg merge: 2h 57m
Merged PRs (30d): 2

Dominant language: Python
License: Apache-2.0
Last GitHub push: Aug 27, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

72 open issues indexed

DreamX-World: A General-Purpose Interactive World Model Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#135 · Opened Jun 18, 2026
请求新增 RTX 5090 平台 FP8 推理优化分支 Open

Difficulty 5/5 Over a week Newbie friendliness 28/100

thu-ml/TurboDiffusion#131 · Opened Jun 10, 2026
关于merge的一些疑问 Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#130 · 7 reactions · Opened Jun 3, 2026
能否支持多卡并行推理呢？ Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#128 · Opened May 29, 2026
请问当前支持在NPU安装，推理吗？ Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#127 · Opened May 27, 2026
Strategy for applying rCM with Autoregressive Student Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#126 · 1 comment · Opened Apr 26, 2026
关于wan 2.2 5B模型支持 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#124 · Opened Mar 20, 2026
net.load_state_dict(state_dict, assign=True) 失败 Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#122 · 1 comment · Opened Mar 9, 2026
Generalization of the merging operation Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#121 · 2 comments · Opened Mar 9, 2026
hello,请教下关于模型兼容性的问题 Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#120 · 3 comments · Opened Mar 5, 2026
Illegal Memory Access on 5090 Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

thu-ml/TurboDiffusion#119 · 1 comment · Opened Mar 5, 2026
QA What benchmark/dataset is used for evaluations? Open

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

thu-ml/TurboDiffusion#118 · Opened Feb 25, 2026
sla是全参微调吗，还是只训练SparseLinearAttention？ Open

Difficulty 1/5 Under an hour Newbie friendliness 20/100

thu-ml/TurboDiffusion#117 · 3 comments · Opened Feb 25, 2026
Question about different patch embedding implementation compared to official Wan-Video Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#114 · 1 comment · Opened Feb 14, 2026
How is the performance if we train with sCM loss only? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#111 · 1 comment · Opened Feb 1, 2026
Sparse Linear Layer weights are 0 for 14B 480p model Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#109 · Opened Jan 27, 2026
帧率比较低？ Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

thu-ml/TurboDiffusion#108 · 1 comment · Opened Jan 27, 2026
推理效果 Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#107 · 1 comment · Opened Jan 27, 2026
merge逻辑 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#105 · 2 comments · Opened Jan 23, 2026
[Benchmark] Inference Performance on RTX 5090 with Wan2.1-1.3B (PyTorch 2.8.0) Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#102 · 1 comment · Opened Jan 19, 2026
你好，请教一下作者是怎么将原始wan2.1的tensor 格式，转成pth格式的 Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

thu-ml/TurboDiffusion#101 · 1 comment · Opened Jan 16, 2026
你好，为什么在尝试SLA训练时，会卡在这里 Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

thu-ml/TurboDiffusion#100 · 2 comments · Opened Jan 16, 2026
loss 0.0000 Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#99 · 5 comments · Opened Jan 16, 2026
NotImplementedError Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#97 · 2 comments · Opened Jan 15, 2026
wan s2v有计划加入进来吗 Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

thu-ml/TurboDiffusion#96 · Opened Jan 15, 2026
其他视频模型 Open

Difficulty 5/5 Over a week Newbie friendliness 18/100

thu-ml/TurboDiffusion#94 · 3 comments · Opened Jan 14, 2026
lora微调 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#93 · 5 comments · Opened Jan 14, 2026
项目训练时间 Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#92 · 4 comments · Opened Jan 13, 2026
Reproducing results on RTX 5090 (sm120): SpargeAttention compatibility and environment setup Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

thu-ml/TurboDiffusion#91 · 1 comment · Opened Jan 12, 2026
如何添加负向提示词？ Open

Difficulty 2/5 1-3 hours Newbie friendliness 25/100

thu-ml/TurboDiffusion#89 · 1 comment · Opened Jan 9, 2026
TurboWan2.1 only apply rCM Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#87 · 1 comment · Opened Jan 8, 2026
提示词控制有点欠缺 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#85 · 3 comments · Opened Jan 8, 2026
raise an error at RTX 5090 Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#83 · 3 comments · Opened Jan 7, 2026
Can TurboDiffusion be applied to Autoregressive generation in a training-free manner? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#81 · 1 comment · Opened Jan 6, 2026
报错 nvcc fatal : Unsupported gpu architecture 'compute_120a' Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#80 · 1 comment · Opened Jan 6, 2026
4090 - 24G出现 OOM Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#78 · 3 comments · Opened Jan 5, 2026
Merge_models.py doesn't merge SLA's proj_l layers? Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

thu-ml/TurboDiffusion#77 · 3 comments · Opened Jan 5, 2026
Killed进程被杀死 Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#76 · 2 comments · Opened Jan 4, 2026
How to train Wan2.2 I2V from scratch? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#75 · 1 comment · Opened Jan 2, 2026
Lora fine tuning Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

thu-ml/TurboDiffusion#72 · 2 comments · Opened Jan 1, 2026
How to run original Wan-2.2 A14B 720p on a single RTX 5090 Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#71 · 1 comment · Opened Jan 1, 2026
Runtime Error Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#67 · 3 comments · Opened Dec 30, 2025
Can WAN Move work with Turbo Diffusion Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#63 · 1 comment · Opened Dec 30, 2025
how to speed up model switching? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

thu-ml/TurboDiffusion#57 · 7 comments · Opened Dec 27, 2025
Enhancement Request: Gradio Interface Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

thu-ml/TurboDiffusion#56 · Opened Dec 27, 2025
Enhancement Request: Post-Install Check Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#55 · Opened Dec 27, 2025
Enhancement Request: Environment Health Check Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#54 · Opened Dec 27, 2025
Running a 5090 and getting OOM errors on 720p resolution Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#52 · 11 comments · Opened Dec 26, 2025
5090 Video Generation is around 79s (reported 38s). Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

thu-ml/TurboDiffusion#51 · 3 comments · 1 reaction · Opened Dec 26, 2025
Install Error Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

thu-ml/TurboDiffusion#50 · Opened Dec 26, 2025

thu-ml/TurboDiffusion

Get new issues in your inbox