gptq topic

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

intel

🪶 Lightweight OpenAI drop-in replacement for Kubernetes

chenhunghan

Large Language Models for All, 🦙 Cult and More, Stay in touch !

shm007g

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

BobaZooba

A guide about how to use GPTQ models with langchain

abhinand5

Run any Large Language Model behind a unified API

1b5d

zero零训练llm调参

ziwang-com

SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

intel