A tool for model sparse based on torch.fx

CUDA Library Samples

This is the official PyTorch implementation of "LLM-QBench: A Benchmark Towards the Best Practice for Post-training Quantization of Large Language Models", and also an efficient LLM compression too…

本项目旨在分享大模型相关技术原理以及实战经验。

FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。

Must-read Papers on LLM Agents.

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

Solve puzzles. Learn CUDA.

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

Awesome LLM compression research papers and tools.

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

Offline Quantization Tools for Deploy.

GPTQ inference Triton kernel

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

TensorRT 7 C++ (almost) minimal examples

PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity

A latent text-to-image diffusion model

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Pretrained models on CIFAR10/100 in PyTorch

Classification with PyTorch.

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas lik…

A PyTorch implementation of SSDLite on COCO

Pytorch implementation of RetinaNet object detection.

An Efficient Framework for Fast UAV Exploration

Prune DNN using Alternating Direction Method of Multipliers (ADMM)

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

Pytorch implementation of various Knowledge Distillation (KD) methods.