leesou

leesou's Stars

• LC044/WeChatMsg

  提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

  Language:Python32.8k1703993.4k

• facebookresearch/faiss

  A library for efficient similarity search and clustering of dense vectors.

  Language:C++30.4k4822.5k3.5k

• vllm-project/vllm

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

  Language:Python26.1k2254.3k3.8k

• taskflow/taskflow

  A General-purpose Task-parallel Programming System using Modern C++

  Language:C++10k2574521.2k

• SJTU-IPADS/PowerInfer

  High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

  Language:C++7.9k75155401

• OpenMathLib/OpenBLAS

  OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

  Language:C6.3k2062.3k1.5k

• nmslib/hnswlib

  Header-only C++/python library for fast approximate nearest neighbors

  Language:C++4.2k64364623

• ray-project/llm-numbers

  Numbers every LLM developer should know

  4k5917136

• oneapi-src/oneDNN

  oneAPI Deep Neural Network Library (oneDNN)

  Language:C++3.6k1861.3k984

• mengjian-github/copilot-analysis

  Language:JavaScript2k217239

• jeonsworld/ViT-pytorch

  Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

  Language:Jupyter Notebook1.9k1355362

• fengbintu/Neural-Networks-on-Silicon

  This is originally a collection of papers on neural network accelerators. Now it's more like my selection of research on deep learning and computer architecture.

  1.8k3013381

• flexflow/FlexFlow

  FlexFlow Serve: Low-Latency, High-Performance LLM Serving

  Language:C++1.6k33642223

• corundum/corundum

  Open source FPGA-based NIC and platform for in-network compute

  Language:Verilog1.6k89161410

• hao-ai-lab/LookaheadDecoding

  [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

  Language:Python1.1k115563

• libxsmm/libxsmm

  Library for specialized dense and sparse matrix operations, and deep learning primitives.

  Language:C83950336180

• feifeibear/LLMSpeculativeSampling

  Fast inference from large lauguage models via speculative decoding

  Language:Python49021447

• ray-project/llmperf-leaderboard

  416151013

• cli99/llm-analysis

  Latency and Memory Analysis of Transformer Models for Training and Inference

  Language:Python3338938

• pbsinclair42/MCTS

  A simple package to allow users to run Monte Carlo Tree Search on any perfect information domain

  Language:Python19971169

• FasterDecoding/REST

  REST: Retrieval-Based Speculative Decoding, NAACL 2024

  Language:C15851410

• abdelazeem201/Systolic-array-implementation-in-RTL-for-TPU

  IC implementation of Systolic Array for TPU

  Language:Verilog1302122

• NVIDIA-Merlin/HierarchicalKV

  HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of HierarchicalKV is to store key-value feature-embeddings on high-bandwidth memory (HBM) of GPUs and in host memory. It also can be used as a generic key-value storage.

  Language:Cuda126192525

• microsoft/ark

  A GPU-driven system framework for scalable AI applications

  Language:C++101121815

• VIA-Research/uPIMulator

  Language:C792411

• miglopst/PIM_NDP_papers

  6012018

• facebookresearch/dlrm_datasets

  Set of datasets for the deep learning recommendation model (DLRM).

  3971015

• AIS-SNU/Smart-Infinity

  [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System

  Language:Python33103

• HPCRL/ASPLOS_artifact

  Language:C141503

• yester31/OneDNN_EX

  Deep Learning model with OneDNN

  Language:C++4200