테스트를 위한 TurboDiffusion fork
Python · active 2025-12-15 → 2026-07-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 218 days from 2025-12-15 to 2026-07-20. Pushes: 32 total, peak 6 in a day. Pull requests: 8 total, peak 1 in a day. Issues: 63 total, peak 5 in a day. Comments: 99 total, peak 15 in a day. Stars: 1,471 total, peak 258 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| zhengkw18 | 38 | 20 | 0 | 18 |
| jt-zhang | 28 | 10 | 0 | 9 |
| whx1003 | 15 | 4 | 0 | 9 |
| zwukong | 11 | 0 | 0 | 7 |
| MrEdwards007 | 7 | 0 | 0 | 4 |
| johndpope | 4 | 0 | 1 | 3 |
| leeruibin | 4 | 0 | 0 | 2 |
| xFinal | 3 | 0 | 0 | 1 |
| bat3a | 3 | 0 | 0 | 3 |
| StriveZs | 3 | 0 | 0 | 2 |
| ckfanzhe | 3 | 0 | 0 | 3 |
| whalemjy | 3 | 0 | 0 | 1 |
| xiaoyehaosao-jpg | 2 | 0 | 0 | 0 |
| OldZhao | 2 | 0 | 0 | 1 |
| fanyules | 2 | 0 | 0 | 1 |
| xiaoxuexiaoniu | 2 | 0 | 0 | 2 |
| Franc1sCai | 2 | 0 | 0 | 1 |
| ivanium | 2 | 0 | 2 | 0 |
| yy99299 | 2 | 0 | 0 | 1 |
| yysixxxxxx | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue#128yxqyyy2026-05-29 02:53能否支持多卡并行推理呢？
- Issue#125wdmzswjx2026-03-20 04:06请问有关E2E时间的测度，是DiT的降噪时间，还是端到端生成视频的时间？我自己测试的生成时间加上vae.decode整体加速比并没有论文中那么大
- Issue#124weiyithu2026-03-20 03:08关于wan 2.2 5B模型支持
- Issue#122JackBlue3022026-03-09 09:05net.load_state_dict(state_dict, assign=True) 失败
- Issue comment#119ChenNingCong2026-03-08 12:17Illegal Memory Access on 5090
- Issue comment#117wzr01082026-03-02 03:26sla是全参微调吗，还是只训练SparseLinearAttention？
- Issue comment#117zhengkw182026-03-01 08:19sla是全参微调吗，还是只训练SparseLinearAttention？
- Issue#115Z-Z1882026-02-24 05:32diffusion 延迟
- Issue comment#113liuyuxiang10212026-02-14 16:13请问非量化满血的turbowan2.2需要在至少40G以上设备上跑，这里48G的足够吗
- Issue comment#113zhengkw182026-02-14 07:54请问非量化满血的turbowan2.2需要在至少40G以上设备上跑，这里48G的足够吗
- Issue comment#114zhengkw182026-02-14 07:52Question about different patch embedding implementation compared to official Wan-Video
- Issue#114ChenJiongxu3552026-02-14 07:05Question about different patch embedding implementation compared to official Wan-Video
- Issue comment#105zhengkw182026-02-05 14:03merge逻辑
- Issue#111meng-ustc2026-02-01 00:27How is the performance if we train with sCM loss only?
- Pull request#110minorun19682026-01-31 00:18
- Issue#109ulucsahin2026-01-27 10:39Sparse Linear Layer weights are 0 for 14B models
- Issue comment#97chengby23592026-01-23 08:18NotImplementedError
- Issue comment#80plumbagella2026-01-22 06:53报错 nvcc fatal : Unsupported gpu architecture 'compute_120a'
- Issue#26jt-zhang2026-01-17 17:35OutOfMemoryError: Allocation on device
- Issue comment#12jt-zhang2026-01-17 17:35TurboWan2.2-T2V-A14B-720P?
- Issue#39jt-zhang2026-01-17 17:34A800 可以使用非量化版本推理么？
- Issue#27jt-zhang2026-01-17 17:32希望添加V100显卡支持
- Issue comment#95jt-zhang2026-01-17 17:28关于W8A8量化
- Issue comment#98jt-zhang2026-01-17 17:27Plans to support HunyuanVideo-1.5
- Issue comment#88jt-zhang2026-01-17 17:26在A800上提速效果如何？我测试的只提速了大概4倍
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,471 stars here means stars gained during the window, not the repo's star count.