A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning
Repository Index
47,133 repositories indexed
1–7 of 7 · Most stars
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
Library and utilities to read and write broadcasting media files. Primarily supports the MXF file format
Windows tool to display the internal structure of an MXF (Material eXchange Format) file
- mxf
- inspect
- analyzer
- broadcast
F# Type Providers for SqlDataConnection, SqlEntityConnection, ODataService, WsdlService and EdmxFile using .NET Framework generators
Media Authoring with Java API - for MXF, AAF, IMF and Reg-XML
Streaming MXF library for Node.js