Convert the cookies from Chrome's Application -> Storage -> Cookies, into the Netscape format accepted by youtube-dl

code for AdaScale MLSys'19 https://proceedings.mlsys.org/book/275.pdf

A scalable inference server for models optimized with OpenVINO™

2023年最新整理 c++后端开发，1000篇优秀博文，含内存，网络，架构设计，高性能，数据结构，基础组件，中间件，分布式相关

The ffmpegcv is a ffmpeg backbone for open-cv like Video Reader and Writer

Intel developer staging area for unmerged upstream patch contributions to FFmpeg

A small ffmpeg-based framebuffer media player

SEPE-8K-Dataset

Thoughts on Go performance optimization

Code samples related to Intel(R) AMX

A curated list of OpenVINO based AI projects

GStreamer学习以及资料整理

Efficient virtual system-on-chip on heterogeneous hardware

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)

Rcmp: Reconstructing RDMA-based Memory Disaggregation via CXL

Low-latency and memory-efficient paging over RDMA networks

This is object detection demo using DLStreamer and OpenVINO to run on Intel® CPU and iGPU

Deployed YOLOX to DL Streamer.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Fast Inference of MoE Models with CPU-GPU Orchestration

A benchmark framework for decision forest inferences

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

LLM Inference benchmark

Supplementary material to paper "Extract-Transform-Load for Video Streams"

EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions

(Research) reduce the use of expensive object detectors when searching large video repos via clever sampling algorithms that account for redundancy in video

Perceptual video quality assessment based on multi-method fusion.