fp8
There are 8 repositories under fp8 topic.
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
Azure/MS-AMP
Microsoft Automatic Mixed Precision Library
intel/neural-speed
An innovative library for efficient LLM inference via low-bit quantization
aredden/flux-fp8-api
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
graphcore-research/jax-scalify
JAX Scalify: end-to-end scaled arithmetics
klessydra/spike-with-minifloat-fp8-support
Spike, a RISC-V ISA Simulator with added 8-bit vector floating point support
zsxkib/cog-step-video-t2v
Cog Single GPU Quantized Implementation of Step-Video-T2V
umangyadav/py_fp8
FP8 dtypes enumeration in python