NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆100Jun 16, 2025Updated last year
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆329Jun 10, 2025Updated last year
- ☆40Nov 28, 2024Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆63Mar 5, 2025Updated last year
- [PACT'24] GraNNDis. A fast and unified distributed graph neural network (GNN) training framework for both full-batch (full-graph) and min…☆10Aug 13, 2024Updated last year
- ☆20May 11, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading☆25Jan 6, 2026Updated 6 months ago
- ☆264Dec 25, 2025Updated 7 months ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆149Feb 22, 2026Updated 5 months ago
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆96May 14, 2026Updated 2 months ago
- Fast OS-level support for GPU checkpoint and restore☆285Sep 28, 2025Updated 9 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆826Apr 6, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆310May 1, 2025Updated last year
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆53Jan 8, 2026Updated 6 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆47May 13, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The official implementation of OSDI'25 paper BlitzScale☆48Apr 15, 2026Updated 3 months ago
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆52Jul 21, 2025Updated last year
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆646Jul 25, 2025Updated last year
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆506Jul 17, 2026Updated last week
- High performance Transformer implementation in C++.☆155Jan 18, 2025Updated last year
- An Observability Framework for AI Training☆73Jul 16, 2026Updated last week
- Efficient and easy multi-instance LLM serving☆563Mar 12, 2026Updated 4 months ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆1,115Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆216Jul 19, 2026Updated last week
- [CPAL 2026 oral] Offical implementation of "ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning”☆16Apr 21, 2026Updated 3 months ago
- PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]☆61Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆969Mar 29, 2026Updated 3 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆139Nov 26, 2025Updated 8 months ago
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆75Mar 11, 2026Updated 4 months ago
- This is the respository that holds the artifacts of ASPLOS'25 -- M5: Mastering Page Migration and Memory Management for CXL-based Tiered …☆17Apr 1, 2025Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆321Updated this week
- ☆24Mar 7, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆140Jul 9, 2026Updated 2 weeks ago
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated last month
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,999Updated this week
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- ☆19Feb 18, 2025Updated last year
- AgentCgroup: Understanding and Controlling OS Resources of AI Agents☆61Updated this week
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆340Jul 16, 2026Updated last week