NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆84Jun 16, 2025Updated 8 months ago
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below
Sorting:
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆314Jun 10, 2025Updated 8 months ago
- This is the respository that holds the artifacts of ASPLOS'25 -- M5: Mastering Page Migration and Memory Management for CXL-based Tiered …☆16Apr 1, 2025Updated 11 months ago
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 3 years ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆52Mar 5, 2025Updated 11 months ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆124Feb 22, 2026Updated last week
- The official implementation of OSDI'25 paper BlitzScale☆41Sep 20, 2025Updated 5 months ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆22Oct 20, 2024Updated last year
- A Framework for Automated Validation of Deep Learning Training Tasks☆62Feb 13, 2026Updated 2 weeks ago
- Fast OS-level support for GPU checkpoint and restore☆271Sep 28, 2025Updated 5 months ago
- Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores (EuroSys'25)☆14Jul 17, 2025Updated 7 months ago
- ☆54Sep 18, 2025Updated 5 months ago
- An optimized Merkle Patricia Trie implementation on GPU, fully compatible with and integrable into Ethereum. The paper is published on VL…☆14Apr 15, 2024Updated last year
- Fast and memory-efficient exact attention☆18Feb 23, 2026Updated last week
- A distributed in-memory store for temporal knowledge graphs☆10Mar 20, 2024Updated last year
- Artifact evaluation for Dogfood☆12Feb 22, 2020Updated 6 years ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆283May 1, 2025Updated 10 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆777Apr 6, 2025Updated 10 months ago
- Low overhead tracing library and trace visualizer for pipelined CUDA kernels☆131Nov 26, 2025Updated 3 months ago
- ☆87Jan 22, 2026Updated last month
- OSDI'24 Nomad implementation☆55Aug 1, 2025Updated 7 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆61Feb 2, 2026Updated last month
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆285Dec 5, 2025Updated 2 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆12Nov 8, 2024Updated last year
- LoRAFusion: Efficient LoRA Fine-Tuning for LLMs☆24Sep 23, 2025Updated 5 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Jul 10, 2024Updated last year
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆162Jan 27, 2026Updated last month
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆80Dec 18, 2025Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆464May 30, 2025Updated 9 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆284Updated this week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41May 13, 2025Updated 9 months ago
- Tiered memory management☆89Sep 1, 2025Updated 6 months ago
- Simple task offloading client to offload HTTP requests to edge servers☆10Dec 8, 2022Updated 3 years ago
- ☆15Apr 15, 2025Updated 10 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆77Oct 15, 2025Updated 4 months ago
- PA + Labs for Operating Systems 2019 course in NJU taught by JYY.☆12Aug 6, 2019Updated 6 years ago
- A resume template written in typst, designed for zh_CN.☆13Mar 3, 2025Updated last year
- CXL remote offloading data movement aware compiler☆73Updated this week
- ☆18Feb 18, 2025Updated last year
- Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆29Sep 12, 2025Updated 5 months ago