推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.
- calibration
- causal-inference
- cold-start
- contrastive-learning
111,821 visible repositories in the index
145–168 of 315 · Most stars
推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
Bootstrapping your personal Web3 info hub from more than 600 RSS Feeds.
Indico - A feature-rich event management system, made @ CERN, the place where the Web was born.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Adaptive Test-time Learning and Autonomous Specialization
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
Pika H3 Flex: video and audio generation inference
Command-line utility to transcribe/translate from video/audio/subtitles to subtitles
Gaussian processes in TensorFlow
Publications from Trail of Bits
Large-scale LLM inference engine
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
基于PaddleOCR重构,并且脱离PaddlePaddle深度学习训练框架的轻量级OCR,推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
TensorFlow template application for deep learning
The Offensive Manual Web Application Penetration Testing Framework.
GPT-SoVITS ONNX Inference Engine & Model Converter
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
High Performance Serving Runtime For Interactive Super Intelligence System
Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.