NEO-MLSys25 / NEOLinks
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆67Updated 4 months ago
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below
Sorting:
- ☆57Updated last week
- Stateful LLM Serving☆88Updated 7 months ago
- ☆75Updated 3 weeks ago
- ☆124Updated 11 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆157Updated last year
- A framework for generating realistic LLM serving workloads☆76Updated last month
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆98Updated last month
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆69Updated 3 weeks ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆35Updated 5 months ago
- High performance Transformer implementation in C++.☆140Updated 9 months ago
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆73Updated 2 weeks ago
- ☆147Updated 3 months ago
- A lightweight design for computation-communication overlap.☆183Updated 3 weeks ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆216Updated 3 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆131Updated last year
- ☆27Updated last year
- ☆13Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆126Updated 3 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆42Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆150Updated 9 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆189Updated last year
- Distributed MoE in a Single Kernel [NeurIPS '25]☆89Updated last month
- LLM serving cluster simulator☆116Updated last year
- ☆79Updated 3 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆142Updated last month
- ☆137Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆42Updated 8 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆102Updated 2 years ago
- Compiler for Dynamic Neural Networks☆46Updated last year