AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

大数据入门指南 ⭐

[ICML 2024] Official PyTorch implementation of "SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization"

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

A high-throughput and memory-efficient inference and serving engine for LLMs

[TMLR 2024] Efficient Large Language Models: A Survey

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

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

LightSeq: A High Performance Library for Sequence Processing and Generation

The PyTorch implementation of Learned Step size Quantization (LSQ) in ICLR2020 (unofficial)

中国大模型

Grok open release

Official inference library for Mistral models

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

The official implementation of the ICML 2023 paper OFQ-ViT

Running BERT without Padding

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Transformer related optimization, including BERT, GPT

Modeling, training, eval, and inference code for OLMo

Implementation of "DeepShift: Towards Multiplication-Less Neural Networks" https://arxiv.org/abs/1905.13298

Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models".

Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"

[EMNLP 2022 main] Code for "Understanding and Improving Knowledge Distillation for Quantization-Aware-Training of Large Transformer Encoders"

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

QLoRA: Efficient Finetuning of Quantized LLMs

【编程随想】整理的《太子党关系网络》，专门揭露赵国的权贵