alibaba/MNN

MNN

✅ Recently maintained

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

16,341Stars
2,497Forks
+477-day stars

C++ · Apache-2.0 · Last push 2026-11-03

Official repository & installation ↗
mnnconvolutionvulkanembedded-deviceswinograd-algorithmmachine-learningdeep-learningmlarmllm

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-0516,158
2026-10-0616,169
2026-10-0716,177
2026-10-0816,180
2026-10-0916,188
2026-10-1016,195
2026-10-1116,197
2026-10-1216,203
2026-10-1316,211
2026-10-1416,219
2026-10-1516,223
2026-10-1616,227
2026-10-1716,230
2026-10-1816,238
2026-10-1916,247
2026-10-2016,250
2026-10-2116,256
2026-10-2216,266
2026-10-2316,272
2026-10-2416,273
2026-10-2516,279
2026-10-2616,291
2026-10-2716,300
2026-10-2816,305
2026-10-2916,306
2026-10-3016,317
2026-10-3116,324
2026-11-0116,332
2026-11-0216,340
2026-11-0316,341

Get the project

git clone https://github.com/alibaba/MNN.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

★ 44,189onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

★ 22,216