Stars
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).
An I/O benchmark for deep Learning applications
Inspektor Gadget is a set of tools and framework for data collection and system inspection on Kubernetes clusters and Linux hosts using eBPF
A lightweight, lightning-fast, in-process vector database
russfellows / mlc-storage
Forked from mlcommons/storageRuss-Fellows Development Branch of : MLPerf Storage Benchmark Suite v3
Evolve your language agent with Agentic Context Engineering (ACE)
Pagemon is an interactive memory/page monitoring tool allowing one to browse the memory map of an active running process.
[ACL 2026] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A multi-protocol storage performance testing tool, inspired by vdbench, fio and warp. Part of the SAI3 project. Leverages the s3dlio Rust library
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
profintegra / raptor-rag
Forked from parthsarthi03/raptorThe official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Running large language models on a single GPU for throughput-oriented scenarios.
First Latency-Aware Competitive LLM Agent Benchmark
The simplest, highest-throughput Python interface to S3, GCS & Azure Storage, powered by Rust.
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Part of the sai3 project that delivers multi-protocol storage access for AI/ML workflows, supporting Pytorch, Tensorflow and Jax. This project provides a CLI, along with Rust and Python libraries f…