fp8

There are 0 repository under fp8 topic.

NVIDIA / TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
cuda deep-learning gpu machine-learning python pytorch fp8 jax
Language:Python 1518
Azure / MS-AMP
Microsoft Automatic Mixed Precision Library
amp deep-learning fp8 gpu pytorch transformer mixed-precision
Language:Python 469
intel / neural-speed
An innovative library for efficient LLM inference via low-bit quantization
cpu fp8 gaudi2 gpu int4 int8 llm-inference low-bit sparsity fp4 llm-fine-tuning mxformat nf4 llamacpp int2 int3 int5 int6 int7 int1
Language:C++ 282
klessydra / spike-with-minifloat-fp8-support
Spike, a RISC-V ISA Simulator with added 8-bit vector floating point support
fp8 minifloat riscv spike
Language:C 1
umangyadav / py_fp8
FP8 dtypes enumeration in python
fp8 fp8e4m3 fp8e4m3fnuz fp8e5m2 fp8e5m2fnuz
Language:C++ 0

NVIDIA / TransformerEngine