7 projects
onnx-benchy
Benchmark ONNX embedding models across ONNX Runtime backends
ternary-QAT
Ternary QAT for transformers, built for Ternary-Bonsai by Prism-ML
quant-clone
Generate a llama-quantize command to copy the quantization parameters of any GGUF
dataset-build
Build a multilingual dataset for imatrix or quantization calibration of LLMs or embedding models
gpu-list
List GPUs and VRAM amounts in Windows and Linux
pyatomix
Cross platform atomic int for Python
atomix-base
atomics for pyatomix
