dongqishen Goto Github PK

aurora

autoawq

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

awesome-cheatsheets

👩‍💻👨‍💻 Awesome cheatsheets for popular programming languages, frameworks and development tools. They include everything you should know in one single file.

blislab

BLISlab: A Sandbox for Optimizing GEMM

codeforces

AC

cs143

CS143 learning and assignments

cs143-compilers-stanford

My solutions to the programming assignments of the Stanford Compiler course.

deep_learning_interview

深度学习面试总结

dongqishen.github.io

Dongqi's Leisure Time

dongqishen.github.io_2

Dongqi's leisure time.

dongqishen.github.io_archive

🍎Jalpc -- A flexible Jekyll theme, 3 steps to build your website.

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

flashattention-pytorch

Implementation of FlashAttention in PyTorch

ggml

Tensor library for machine learning

google-hosts

Google hosts generator

gptpdf

Using GPT to parse PDF

gradio

Create UIs for your machine learning model in Python in 3 minutes

hosts

镜像：https://scaffrey.coding.net/p/hosts/git / https://git.qvq.network/googlehosts/hosts

iblog-server

服务器上的网站源码

igemm

igemm tutorial

illm

Implementing LLM from scratch. (Developing...)

ips

优选ip

kaleidoscope

A toy language called “Kaleidoscope” (derived from “meaning beautiful, form, and view”). Kaleidoscope is a procedural language that allows you to define functions, use conditionals, math, etc.

llama.cpp

Port of Facebook's LLaMA model in C/C++

llm.c

LLM training in simple, raw C/CUDA

llm_interview_note

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

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.

llvm-tutor

A collection of out-of-tree LLVM passes for teaching and learning

mlx-examples

Examples in the MLX framework

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.