Skip to content

Issues: alibaba/MNN

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

32 Open 2,576 Closed
32 Open 2,576 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

OpenCL 配置共享运行时，出现崩溃
#3100 opened Nov 25, 2024 by Jerry3062
错误的断言 MNN_ASSERT(srcBuffer.dimensions == dstBuffer.dimensions);
#3099 opened Nov 25, 2024 by tp-nan
Qwen2.5-0.5B-Instruct 8bit量化 动态加载LoRA精度下降严重
#3098 opened Nov 24, 2024 by jfduma
MNN结果和onnx结果不一致，mnn结果错误
#3097 opened Nov 22, 2024 by gtfaiwxm
MNN怎么输出log日志 User The user ask question about how to use. Or don't use MNN correctly and cause bug.
#3096 opened Nov 22, 2024 by SigalZhang
1
Qwen2.5-0.5B-Instruct 运行apply_lora.py失败 bug Something isn't working llm llm export error or use error
#3095 opened Nov 20, 2024 by jfduma
1
MNN does not use GPU mail-G31 for inference on android question Further information is requested
#3093 opened Nov 20, 2024 by trungnb34
4
Qwen2.5-0.5B-Instruct 8bit量化 推理输出乱码 bug Something isn't working
#3091 opened Nov 19, 2024 by jfduma
6
新的硬件后端接入 User The user ask question about how to use. Or don't use MNN correctly and cause bug.
#3090 opened Nov 19, 2024 by chayliu1991
1
mnn推理时如何降低内存占用 User The user ask question about how to use. Or don't use MNN correctly and cause bug.
#3086 opened Nov 16, 2024 by lxh0510
2
MNN conversion failing backend test for RT DETR model bug Something isn't working CUDA question Further information is requested
#3085 opened Nov 15, 2024 by jasseeeem
3
编译MNN 打开-DMNN_KLEIDIAI=ON 后，LLM推理选择opencl后端推理结果异常 bug Something isn't working
#3077 opened Nov 13, 2024 by ZhiquanWoW
1
useing mnncv image process get wrong result question Further information is requested
#3076 opened Nov 13, 2024 by jfkkf123
8
希望能补充说明文档中mnnquant、MNNPythonOfflineQuant、mnncompress可运行examples的源码 Suggestion
#3075 opened Nov 13, 2024 by chenshumeng
使用quantized.out进行多输入序列模型量化出错 bug Something isn't working
#3073 opened Nov 11, 2024 by LXWLZU
2
onnx_export.py 报错 question Further information is requested
#3072 opened Nov 5, 2024 by BigFaceBoy
1
Any plan support latest version on vcpkg? Suggestion
#3070 opened Nov 3, 2024 by foobra
ConvTranspse算子执行发生段错误 duplicate This issue or pull request already exists
#3067 opened Oct 30, 2024 by SheepHuan
1
在nvidia jetson orin nx 上 启用cuda和tensorrt 编译失败，tensorrt里面的调用api太老了，该如何解决 bug Something isn't working
#3064 opened Oct 29, 2024 by captain0005
2
macos15下，app的名称是三字中文，启动MNN推理就会崩溃。 bug Something isn't working
#3063 opened Oct 24, 2024 by acezhx
4
CPU推理时ConvTranspose算子内存占用太大 bug Something isn't working
#3061 opened Oct 24, 2024 by dingithub365
intel subgroup支持异常 bug Something isn't working
#3059 opened Oct 23, 2024 by zeekimn
4
MNN int8量化模型GetMNNInfo无法加载模型，返回Segmentation fault question Further information is requested
#3058 opened Oct 22, 2024 by codingSellena
6
使用OPENCL推理结果出现段错误，CPU结果正常。 question Further information is requested
#3057 opened Oct 22, 2024 by zhangshabao
1
MNNWorkbench无法登录
#3056 opened Oct 21, 2024 by YZJ0716
ProTip! no:milestone will show everything without a milestone.