zifeitong

zifeitong's Stars

• google/llvm-propeller

  PROPELLER: Profile Guided Optimizing Large Scale LLVM-based Relinker

  Language:Shell35834

• felafax/felafax

  Felafax is building AI infra for non-NVIDIA GPUs

  Language:Jupyter Notebook49425

• brentyi/jaxls

  Sparse nonlinear least squares in JAX

  Language:Python17511

• zml/zml

  High performance AI inference stack. Built for production. @ziglang / @openxla / MLIR / @bazelbuild

  Language:Zig1.6k56

• LaurentMazare/xla-rs

  Experimentation using the xla compiler from rust

  Language:Rust8813

• AlibabaPAI/llumnix

  Efficient and easy multi-instance LLM serving

  Language:Python16012

• google-deepmind/penzai

  A JAX research toolkit for building, editing, and visualizing neural networks.

  Language:Python1.7k50

• NVIDIA/multi-gpu-programming-models

  Examples demonstrating available options to program multiple GPUs in a single node or a cluster

  Language:Cuda547110

• microsoft/BitBLAS

  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

  Language:Python37230

• project-oak/oak

  Meaningful control of data in distributed systems.

  Language:Rust1.3k113

• google/riegeli

  Riegeli/records is a file format for storing a sequence of string records, typically serialized protocol buffers.

  Language:C++41653

• EleutherAI/cookbook

  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

  Language:Python69235

• HPMLL/BurstGPT

  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

  Language:Python1177

• google-research/dex-lang

  Research language for array processing in the Haskell/ML family

  Language:Haskell1.6k107

• bytedance/flux

  A fast communication-overlapping library for tensor parallelism on GPUs.

  Language:C++20215

• pytorch/torchtune

  PyTorch native finetuning library

  Language:Python4.2k399

• vllm-project/llm-compressor

  Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

  Language:Python58849

• scylladb/seastar

  High performance server-side application framework

  Language:C++8.3k1.5k

• facebookexperimental/libunifex

  Unified Executors

  Language:C++1.5k188

• unum-cloud/ucall

  Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️

  Language:C1.1k41

• NVIDIA/stdexec

  `std::execution`, the proposed C++ framework for asynchronous and parallel programming.

  Language:C++1.6k158

• bytedance/monoio

  Rust async runtime based on io-uring.

  Language:Rust3.9k223

• google/aqt

  Language:Python25826

• google/airio

  Language:Python147

• google-deepmind/dm_pix

  PIX is an image processing library in JAX, for JAX.

  Language:Python38622

• NVIDIA/TransformerEngine

  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

  Language:Python1.9k314

• pytorch-labs/gpt-fast

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

  Language:Python5.6k509

• pytorch/serve

  Serve, optimize and scale PyTorch models in production

  Language:Java4.2k855

• skyplane-project/skyplane

  🔥 Blazing fast bulk data transfers between any cloud 🔥

  Language:Python1.1k62

• cli99/llm-analysis

  Latency and Memory Analysis of Transformer Models for Training and Inference

  Language:Python34440