#74 · Primary category： Inference & Local Deploy
ComputeLibrary
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
Project last updated：08/27/26
GitHub Stars
3.2K
Forks
819
Contributors
150
License
Other
Why we included this project
Arm processors show up in everything from phones to cloud servers, and this library is how machine learning gets fast on them. It provides the low-level kernels and convolution algorithms that higher-level runtimes build on, so a model that feels sluggish in a naive port becomes genuinely usable when routed through these primitives. Build options are flexible enough to produce lightweight binaries for embedded targets, and data type support (FP16, INT8, BFLOAT16) spans what most production workloads actually need. It's worth a look whenever you need Arm-optimized compute rather than a full end-to-end inference stack.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.