rebel-jueonpark

rebel-jueonpark's Stars

• bytedance/flux

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

  Language:C++20115

• bloomberg/memray

  Memray is a memory profiler for Python

  Language:Python13.2k394

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.4k947

• llvm/llvm-project

  The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

  Language:LLVM28.5k11.8k

• triton-inference-server/tensorrtllm_backend

  The Triton TensorRT-LLM Backend

  Language:Python67998

• facebookresearch/xformers

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

  Language:Python8.5k605

• pytorch-labs/triton-cpu

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

  Language:C++343

• tenstorrent/tt-buda

  Tenstorrent TT-BUDA Repository

  Language:Python21429

• tenstorrent/tt-metal

  :metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

  Language:C++43159

• open-mpi/ompi

  Open MPI main development repository

  Language:C2.1k859

• nod-ai/SHARK-Studio

  SHARK Studio -- Web UI for SHARK+IREE High Performance Machine Learning Distribution

  Language:Python1.4k170

• fmtlib/fmt

  A modern formatting library

  Language:C++20.6k2.5k

• gcc-mirror/gcc

  Language:C++9.2k4.4k

• nod-ai/techtalks

  16

• facebookresearch/fairscale

  PyTorch extensions for high performance and large scale training.

  Language:Python3.2k279

• microsoft/triton-shared

  Shared Middle-Layer for Triton Compilation

  Language:MLIR17137

• vllm-project/vllm

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

  Language:Python28.4k4.2k

• intel/mlir-extensions

  Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.

  Language:MLIR11944

• triton-inference-server/pytorch_backend

  The Triton backend for the PyTorch TorchScript models.

  Language:C++11943

• modularml/mojo

  The Mojo Programming Language

  Language:Mojo23k2.6k

• mlc-ai/docs

  The documents for TVM Unity

  Language:Shell112

• huggingface/optimum

  🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

  Language:Python2.5k451

• llvm/torch-mlir

  The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

  Language:C++1.3k496

• octoml/relax

  A fork of tvm/unity

  Language:Python1513

• gabime/spdlog

  Fast C++ logging library.

  Language:C++24.1k4.5k

• plaidml/plaidml

  PlaidML is a framework for making deep learning work everywhere.

  Language:C++4.6k400

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++13k1.6k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.8k1.3k

• pytorch/pytorch

  Tensors and Dynamic neural networks in Python with strong GPU acceleration

  Language:Python82.9k22.4k

• ise-uiuc/neuri-artifact

  Artifact for ESEC/FSE'23 paper "NeuRI: Diversifying DNN Generation via Inductive Rule Inference"

  Language:Python295