Stars
FlashInfer: Kernel Library for LLM Serving
Community maintained hardware plugin for vLLM on Ascend
FlashMLA: Efficient MLA decoding kernels
A high-throughput and memory-efficient inference and serving engine for LLMs
The codebase for our ACL2023 paper: Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
[ICLR 2024] Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Cloud Shuffle Service(CSS) is a general purpose remote shuffle solution for compute engines, including Spark/Flink/MapReduce.
NoSQL Redis and Memcache traffic generation and benchmarking tool.
cluster data collected from production clusters in Alibaba for cluster management research
Apache Celeborn is an elastic and high-performance service for shuffle and spilled data.
Apache Kyuubi is a distributed and multi-tenant g 97F7 ateway to provide serverless SQL on data warehouses and lakehouses.
🔨 🍇 💻 🚀 GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba | 一站式图计算系统
databricks / tpcds-kit
Forked from gregrahn/tpcds-kitTPC-DS benchmark kit with some modifications/fixes
PMM dashboards for database monitoring
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many mo…
The Prometheus monitoring system and time series database.
Nightingale for monitoring and alerting, just as Grafana for visualization.
An open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs
A prototype implementation of Bao for PostgreSQL
Flink 中文视频课程（持续更新...）