PyRank

Low Precision Python Packages

Python packages with the GitHub topic low-precision. Sorted by relevance, with stars and monthly downloads.
intel
neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

32K 3K 305
Tiiiger
qtorch

Low Precision Arithmetic Simulation in PyTorch

21K 289 81
intel
neural-compressor-pt

Repository of Intel® Neural Compressor

1K 3K 305
intel
neural-compressor-tf

Repository of Intel® Neural Compressor

1K 3K 305
intel
neural-compressor-full

Repository of Intel® Neural Compressor

464 3K 305
intel
neural-solution

Repository of Intel® Neural Compressor

423 3K 305
intel
neural-insights

Repository of Intel® Neural Compressor

355 3K 305
intel
lpot

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

285 3K 306
graphcore-research
jax-scalify

JAX Scalify: end-to-end scaled arithmetics

126 18 0
intel
ilit

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

105 3K 306
intel
neural-compressor-3x-pt

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

16 3K 305
intel
neural-compressor-3x-ort

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

3 3K 305
intel
neural-compressor-3x-tf

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

3 3K 305