🥇 A curated list of awesome large language models in finance(FinLLMs), including papers,models,datasets and codebases. 金融大模型列表，特别是中英双语大模型。

Modeling, training, eval, and inference code for OLMo

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Learning material for CMU10-714: Deep Learning System

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

TinySTL is a subset of STL(cut some containers and algorithms) and also a superset of STL(add some other containers and algorithms)

从入门到精通，该项目力求做到最清晰、最系统的中文Prompt指北

VideoSys: An easy and efficient system for video generation

Efficient Triton Kernels for LLM Training

A curated list for Efficient Large Language Models

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

计算机自学指南

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

flash attention tutorial written in python, triton, cuda, cutlass

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

4 bits quantization of LLaMA using GPTQ

Development repository for the Triton language and compiler

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Universal LLM Deployment Engine with ML Compilation

Inference Llama 2 in one file of pure C

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

Mamba SSM architecture

Making large AI models cheaper, faster and more accessible

🎉 Modern CUDA Learn Notes with PyTorch: CUDA Cores, Tensor Cores, fp32/tf32, fp16/bf16, fp8/int8, flash_attn, rope, sgemm, hgemm, sgemv, warp/block reduce, elementwise, softmax, layernorm, rmsnorm.