retonym

retonym's Stars

• bitsandbytes-foundation/bitsandbytes

  Accessible large language models via k-bit quantization for PyTorch.

  Language:Python6k606

• meta-llama/llama-recipes

  Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

  Language:Jupyter Notebook11.6k1.6k

• ifromeast/cuda_learning

  learning how CUDA works

  Language:Cuda14818

• DefTruth/CUDA-Learn-Notes

  🎉CUDA/C++ 笔记 / 技术博客: fp32、fp16/bf16、fp8/int8、flash_attn、sgemm、sgemv、warp/block reduce、dot prod、elementwise、softmax、layernorm、rmsnorm、hist etc.

  Language:Cuda1.1k115

• hkproj/pytorch-llama

  LLaMA 2 implemented from scratch in PyTorch

  Language:Python21644

• ollama/ollama

  Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

  Language:Go89k7k

• huihut/interview

  📚 C/C++ 技术面试基础知识总结，包括语言、程序库、数据结构、算法、系统、网络、链接装载库等知识及面试经验、招聘、内推等信息。This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, including language, program library, data structure, algorithm, system, network, link loading library, interview experience, recruitment, recommendation, etc.

  Language:C++34.4k7.9k

• EricPengShuai/Interview

  CPP面试修炼

  Language:C++13216

• mit-han-lab/streaming-llm

  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

  Language:Python6.5k363

• kvcache-ai/Mooncake

  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

  1k22

• FlagOpen/FlagGems

  FlagGems is an operator library for large language models implemented in Triton Language.

  Language:Python24221

• vosen/ZLUDA

  CUDA on ??? GPUs

  Language:Rust8.9k591

• FlagOpen/FlagAttention

  A collection of memory efficient attention operators implemented in the Triton language.

  Language:Python20314

• cuda-mode/awesomeMLSys

  An ML Systems Onboarding list

  48819

• mlops-discord/gpu-optimization-workshop

  Slides, notes, and materials for the workshop

  29630

• mlabonne/llm-course

  Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

  Language:Jupyter Notebook37k3.9k

• NVIDIA/cccl

  CUDA Core Compute Libraries

  Language:C++1.1k131

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook5.7k334

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda23.2k2.6k

• brexhq/prompt-engineering

  Tips and tricks for working with Large Language Models like OpenAI's GPT-4.

  8.3k383

• ModelTC/lightllm

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

  Language:Python2.3k190

• BobMcDear/attorch

  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

  Language:Python45121

• facebookincubator/gloo

  Collective communications library with various primitives for multi-machine training.

  Language:C++1.2k299

• forthespada/CampusShame

  互联网仍有记忆！那些曾经在校招过程中毁过口头offer、意向书、三方的公司！纵然人微言轻，也想尽绵薄之力！

  3.1k151

• xai-org/grok-1

  Grok open release

  Language:Python49.4k8.3k

• microsoft/autogen

  A programming framework for agentic AI 🤖

  Language:Jupyter Notebook30.8k4.5k

• unslothai/unsloth

  Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python15.5k1k

• InternLM/lmdeploy

  LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

  Language:Python4.2k376

• sympy/sympy

  A computer algebra system written in pure Python

  Language:Python12.8k4.4k

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.5k503