Fp8 Python Packages

nvidia-cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

bigsmall

Lossless AI model compression - ~34% smaller with bit-identical weights; the autopilot profiles your machine, picks the highest fidelity that runs, and streams models bigger than your RAM.

neural-speed

An innovative library for efficient LLM inference via low-bit quantization

breccia

Block-scaled FP8 / FP4 / INT4 tensor primitive with Triton scaled-matmul at FP32 parity on H100. NumPy / PyTorch / MLX / JAX backends.

ssblast

First open-source FP8 linear solver for consumer NVIDIA GPUs — 2-3x faster than cuBLAS FP64. pip install ssblast

jax-scalify

JAX Scalify: end-to-end scaled arithmetics