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
facebookresearch/faiss
A library for efficient similarity search and clustering of dense vectors.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
taskflow/taskflow
A General-purpose Task-parallel Programming System using Modern C++
SJTU-IPADS/PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
OpenMathLib/OpenBLAS
OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
nmslib/hnswlib
Header-only C++/python library for fast approximate nearest neighbors
ray-project/llm-numbers
Numbers every LLM developer should know
oneapi-src/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
mengjian-github/copilot-analysis
jeonsworld/ViT-pytorch
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
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.
flexflow/FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
corundum/corundum
Open source FPGA-based NIC and platform for in-network compute
hao-ai-lab/LookaheadDecoding
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
libxsmm/libxsmm
Library for specialized dense and sparse matrix operations, and deep learning primitives.
feifeibear/LLMSpeculativeSampling
Fast inference from large lauguage models via speculative decoding
ray-project/llmperf-leaderboard
cli99/llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
pbsinclair42/MCTS
A simple package to allow users to run Monte Carlo Tree Search on any perfect information domain
FasterDecoding/REST
REST: Retrieval-Based Speculative Decoding, NAACL 2024
abdelazeem201/Systolic-array-implementation-in-RTL-for-TPU
IC implementation of Systolic Array for TPU
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.
microsoft/ark
A GPU-driven system framework for scalable AI applications
VIA-Research/uPIMulator
miglopst/PIM_NDP_papers
facebookresearch/dlrm_datasets
Set of datasets for the deep learning recommendation model (DLRM).
AIS-SNU/Smart-Infinity
[HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System
HPCRL/ASPLOS_artifact
yester31/OneDNN_EX
Deep Learning model with OneDNN