NEO-MLSys25 / NEOLinks
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆64Updated 4 months ago
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below
Sorting:
- ☆52Updated 4 months ago
- Stateful LLM Serving☆86Updated 7 months ago
- ☆124Updated 11 months ago
- ☆72Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆67Updated this week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆103Updated this week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆30Updated 5 months ago
- ☆77Updated 3 years ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆155Updated last year
- ☆140Updated 3 months ago
- A framework for generating realistic LLM serving workloads☆67Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- High performance Transformer implementation in C++.☆135Updated 9 months ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆126Updated this week
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆71Updated this week
- ☆34Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated 2 weeks ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆211Updated 2 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆147Updated 8 months ago
- LLM serving cluster simulator☆116Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆88Updated last month
- A lightweight design for computation-communication overlap.☆181Updated last week
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆101Updated 2 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆138Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆186Updated last year
- ☆26Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆46Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆11Updated 11 months ago