Data

Tools

Indexes

Applications

Experiments

Repos

An open API service providing repository metadata for many open source software ecosystems.

Topic: "sparsegpt"

intel/neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Language: Python - Size: 469 MB - Last synced at: 3 days ago - Pushed at: 4 days ago - Stars: 2,400 - Forks: 267

Related Topics
auto-tuning 1 awq 1 fp4 1 gptq 1 int4 1 int8 1 knowledge-distillation 1 large-language-models 1 low-precision 1 mxformat 1 post-training-quantization 1 pruning 1 quantization 1 quantization-aware-training 1 smoothquant 1 sparsity 1