zyxie

zyxie's Stars

• linkedin/Liger-Kernel

  Efficient Triton Kernels for LLM Training

  Language:Python2.9k145

• scrapy/scrapy

  Scrapy, a fast high-level web crawling & scraping framework for Python.

  Language:Python52.4k10.5k

• livekit/python-sdks

  LiveKit real-time and server SDKs for Python

  Language:Python10133

• google/gemma.cpp

  lightweight, standalone C++ inference engine for Google's Gemma models.

  Language:C++5.9k500

• facebookresearch/xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Language:Python8.3k586

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.1k102

• prometheus/prometheus

  The Prometheus monitoring system and time series database.

  Language:Go54.9k9k

• 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

• hidet-org/hidet

  An open-source efficient deep learning framework/compiler, written in python.

  Language:Python64652

• karpathy/nanoGPT

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

  Language:Python36.2k5.7k

• huggingface/transformers

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

  Language:Python132k26.3k

• huggingface/text-generation-inference

  Large Language Model Text Generation Inference

  Language:Python8.8k1k

• FasterDecoding/Medusa

  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

  Language:Jupyter Notebook2.2k150

• google/aqt

  Language:Python24725

• ptillet/triton-llvm-releases

  Language:Shell2018

• weaviate/weaviate

  Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

  Language:Go10.8k740

• karpathy/llama2.c

  Inference Llama 2 in one file of pure C

  Language:C17.2k2k

• ggerganov/ggml

  Tensor library for machine learning

  Language:C++10.9k1k

• NVIDIA/FasterTransformer

  Transformer related optimization, including BERT, GPT

  Language:C++5.8k882

• microsoft/DeepSpeed

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

  Language:Python34.7k4k

• facebookincubator/AITemplate

  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

  Language:Python4.5k361

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python10k2.2k

• NVIDIA/cutlass

  CUDA Templates for Linear Algebra Subroutines

  Language:C++5.4k904

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++65k9.3k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.4k1.2k

• vllm-project/vllm

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

  Language:Python26.8k3.9k

• twitter/the-algorithm

  Source code for Twitter's Recommendation Algorithm

  Language:Scala62.1k12.1k

• dmlc/xgboost

  Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

  Language:C++26.1k8.7k

• horovod/horovod

  Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

  Language:Python14.2k2.2k

• apache/mxnet

  Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

  Language:C++20.8k6.8k