NEO-MLSys25 / NEOLinks
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆56Updated 2 months ago
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below
Sorting:
- ☆44Updated 2 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆29Updated 3 months ago
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆67Updated 2 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆63Updated 9 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆152Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆21Updated 5 months ago
- ☆116Updated 9 months ago
- ☆69Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆119Updated last week
- ☆75Updated 3 years ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- ☆44Updated last week
- A framework for generating realistic LLM serving workloads☆54Updated 2 months ago
- ☆19Updated 9 months ago
- ☆131Updated last month
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆200Updated last month
- A lightweight design for computation-communication overlap.☆160Updated last week
- LLM serving cluster simulator☆108Updated last year
- A resilient distributed training framework☆94Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆100Updated 2 years 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☆39Updated last week
- An interference-aware scheduler for fine-grained GPU sharing☆145Updated 7 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆66Updated this week
- ☆83Updated 5 months ago
- ☆24Updated last year
- ☆50Updated 2 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆181Updated 11 months ago