alibaba/MNN
View on GitHubMNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
- Stars
- 16.1k
- Forks
- 2.4k
- Open beginner issues
- 0
- Indexed issues
- 20
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 48
- Dominant language
- C++
- License
- Apache-2.0
- Last GitHub push
- Sep 14, 2026
- Latest indexed
- Sep 14, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
-
英特尔gpu 采用opencl 加速异常 Openbackend:opencl platform:windows type:bug
-
app:transformer backend:opencl module:llm platform:android type:bug
-
app:transformer module:llm platform:android type:bug
-
backend:qnn module:llm platform:android type:bug
-
module:llm type:model-request
-
module:llm type:model-request
-
module:llm platform:android type:bug
-
module:llm type:feature
-
module:converter type:bug
-
backend:opencl module:llm type:bug
-
Android API inference crash: SIGABRT in MNN::DeferBufferAllocator::apply() / MNN::Session::resize() Openmodule:llm platform:android type:bug
-
模型在流式输出时文本会上下跳动 Openapp:transformer module:llm platform:android type:bug
-
Android 内存泄露 Openplatform:android type:question
-
app:transformer platform:android type:bug
-
backend:vulkan module:llm platform:windows type:bug
-
platform:android type:question
-
模型对话创建表格bug Opentype:bug