”smoothquant“ 的搜索结果

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

An easy-to-use package for implementing SmoothQuant for LLMs

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

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

Working with SmoothQuant and LLM-AWQ.

Inject errors to LLMs

📖A curated list of Awesome LLM Inference Papers with codes. 🎉🎉