Skip to content

阿里开源MNN TaoAvatar:手机本地运行的3D智能数字人来了

C++ · active 2025-04-052026-08-10 (UTC)

Partial coverage11,184 / 11,820 hourly files (95%) · 2 absent upstream · 634 failed, retryable2025-04-052026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
5K
Pushes
440
Pull requests
248
Issues
759
Stars
2.3K
Forks
229

Activity over time

Daily event counts in the loaded window

Line chart, 493 days from 2025-04-05 to 2026-08-10. Pushes: 440 total, peak 36 in a day. Pull requests: 248 total, peak 9 in a day. Issues: 759 total, peak 55 in a day. Comments: 921 total, peak 19 in a day. Stars: 2,286 total, peak 55 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

ContributorContributionsPushesPRsComments
wangzhaode6863704873
github-actions[bot]35304165
jxt12342855265109
Juude190119123
CLAassistant390039
Qxinyu3410023
abskvrm290010
ihb2032240162
v0jiuqi222020
wohaiaini180010
jules-ai18076
yangy99612007
M17764017422120011
li52477948810004
Yogayu10072
huangzhengxiang9043
bi4key9001
adi-hld8005
changeAtLater8006
quic-zhanweiw7006

Recent activity

Latest issues, pull requests and releases

  • Issue#4706wangzhaode2026-08-09 03:52
    希望添加原生鸿蒙版本华为npu调用
  • Issue#4564wangzhaode2026-06-25 01:13
    视觉模型, 鸿蒙安卓两台手机, cpu算力接近, mnn鸿蒙平台cpu占满, 安卓占有很少
  • Issue#4564wangzhaode2026-06-25 01:13
    视觉模型, 鸿蒙安卓两台手机, cpu算力接近, mnn鸿蒙平台cpu占满, 安卓占有很少
  • Issue#4564wangzhaode2026-06-25 01:13
    视觉模型, 鸿蒙安卓两台手机, cpu算力接近, mnn鸿蒙平台cpu占满, 安卓占有很少
  • Issue#4565wangzhaode2026-06-25 01:13
    英特尔gpu 采用opencl 加速异常
  • Issue#4567wangzhaode2026-06-25 01:13
    [LLM][QNN] QNN context binary generation fails at final lm_head graph on v73 for Qwen3/Qwen3.5 4B
  • Issue#4568wangzhaode2026-06-25 01:13
    请求支持 Qwen3-ASR-0.6B 与 Qwen3-TTS-12Hz-0.6B-Base
  • Issue#4553wangzhaode2026-06-19 01:08
    [MNNCLI] 编译android版本的mnncli失败
  • Issue#4553wangzhaode2026-06-19 01:08
    [MNNCLI] 编译android版本的mnncli失败
  • Pull request#4534DavidVentura2026-06-15 03:19
  • Issue#4462wangzhaode2026-06-12 05:22
    embedding_demo对于不同的文本段,得到的embedding向量数值相同
  • Issue#4462wangzhaode2026-06-12 05:22
    embedding_demo对于不同的文本段,得到的embedding向量数值相同
  • Issue comment#4522jiaohuix2026-06-11 02:01
    Qwen3-0.6B量化后,手机上输出乱码,全是 !!!!!
  • Pull request#4520jxt12342026-06-11 01:16
  • Pull request#4517wangzhaode2026-06-05 10:13
  • Issue comment#4491PencilGo2026-06-03 07:44
    Qwen3-Embedding-0.6B 导出生成 npu backend模型运行失败
  • Issue comment#4475Qxinyu2026-06-03 02:05
    qwen3.5在generate_llm_npu.py编译llm时FusedLinearAttention执行失败,visual执行成功
  • Issue comment#4498cunyuanx2026-06-02 09:17
    [OpenCL][LLM] Mali GPU多轮对话触发page fault;thread_num=4 复现,thread_num=1 可规避
  • Issue comment#4464CLAassistant2026-05-24 00:21
    [Doc:Doc] Fix LLM export option typos
  • Issue comment#4254wangzhaode2026-05-22 02:12
    [MNNConvert:Bugfix] Fix ONNX Resize optional inputs and Einsum weighted sum lowering
  • Issue#4456wangzhaode2026-05-21 05:56
    关于qnn的性能问题,qwen3vl vision的qnn版本比cpu版本慢50%
  • Pull request#4459Fatemanx2026-05-21 02:51
  • Issue comment#4440l00jj2026-05-20 03:03
    qwen3-vl模型 qnn转换以及执行的问题
  • Issue comment#4442wangzhaode2026-05-19 03:16
    mnnconvert with optimizePrefer materializes duplicate weights
  • Issue comment#4433wangzhaode2026-05-18 06:14
    RVV: Optimize common opt functions

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2,286 stars here means stars gained during the window, not the repo's star count.