Search Packages

ctranslate2

Fast inference engine for Transformer models

turbocpp

Fast CPU LLM inference in pure C++17. AVX2+FMA matmul, Q4/Q8 quantization, TurboQuant-style 4/3-bit KV cache, GQA, BPE, mmap loader. Zero deps.

osaca

Open Source Architecture Code Analyzer

corrfunc

⚡️⚡️⚡️Blazing fast correlation functions on the CPU.

ctranslate2-arty

Fast inference engine for Transformer models

adaptq

High-performance CPU KV-cache quantization engine for LLM inference (~10× speedup, 4× memory reduction) with Python & PyTorch support.

residue-protocol

Bare-Metal AVX2 Inference Shield for LLMs

ea-compiler

Eä compute kernel compiler for Python — write SIMD kernels, call from NumPy

detect-simd

Python library to detect CPU SIMD capabilities.

eastat

CSV column statistics powered by Ea SIMD kernels.

pyflagstats

Efficient C functions to compute the summary statistics (flagstats) for sequencing read sets.

easobel

Fast Sobel edge detection. SIMD kernels via Eä, called from Python. 5× faster than OpenCV single-threaded.

eavec

Fast vector similarity search. SIMD kernels via Eä, called from Python. Beats FAISS 4–8× at dim=384.