yiliu30

yiliu30's Stars

• chatanywhere/GPT_API_free

  Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

  Language:Python24.8k1182961.9k

• HigherOrderCO/Bend

  A massively parallel, high-level programming language

  Language:Rust17.5k93259428

• naklecha/llama3-from-scratch

  llama3 implementation one matrix multiplication at a time

  Language:Jupyter Notebook13.7k98181.1k

• adityatelange/hugo-PaperMod

  A fast, clean, responsive Hugo theme.

  Language:HTML10.3k415512.7k

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook10k19232858

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python9.5k48626490

• jzhang38/TinyLlama

  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

  Language:Python7.9k110158466

• NVlabs/tiny-cuda-nn

  Lightning fast C++/CUDA neural network framework

  Language:C++3.8k49392458

• turboderp/exllamav2

  A fast inference library for running LLMs locally on modern consumer-class GPUs

  Language:Python3.7k35462282

• iree-org/iree

  A retargetable MLIR-based machine learning compiler and runtime toolkit.

  Language:C++2.8k884k620

• turboderp/exllama

  A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

  Language:Python2.8k37219220

• 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:Python2.6k23185206

• flame/blis

  BLAS-like Library Instantiation Software Framework

  Language:C2.3k79444369

• neuralmagic/sparseml

  Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

  Language:Python2.1k48206148

• numba/llvmlite

  A lightweight LLVM python binding for writing JIT compilers

  Language:Python1.9k57456319

• HazyResearch/ThunderKittens

  Tile primitives for speedy kernels

  Language:Cuda1.7k292970

• srush/Triton-Puzzles

  Puzzles for learning Triton

  Language:Jupyter Notebook1.1k101383

• pytorch/kineto

  A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

  Language:HTML73225216170

• microsoft/BitBLAS

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

  Language:Python420156834

• FMInference/H2O

  [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

  Language:Python39253842

• KEKE046/mlir-tutorial

  Hands-On Practical MLIR Tutorial

  Language:C++3383346

• fpgaminer/GPTQ-triton

  GPTQ inference Triton kernel

  Language:Jupyter Notebook284122023

• facebookincubator/dynolog

  Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

  Language:C++271162941

• Deep-Learning-Profiling-Tools/triton-viz

  Language:Python15371013

• intel/intel-xpu-backend-for-triton

  OpenAI Triton backend for Intel® GPUs

  Language:MLIR143251.1k44

• gpu-mode/triton-index

  Cataloging released Triton kernels.

  137707

• nod-ai/SHARK-ModelDev

  Unified compiler/runtime for interfacing with PyTorch Dynamo.

  Language:Python953258248

• NVIDIA/online-softmax

  Benchmark code for the "Online normalizer calculation for softmax" paper

  Language:Cuda59607

• iree-org/iree-turbine

  IREE's PyTorch Frontend, based on Torch Dynamo.

  Language:Python55243025

• pytorch-labs/triton-cpu

  An experimental CPU backend for Triton (https//github.com/openai/triton)

  Language:C++351712