NEO-MLSys25 / NEO
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆21Updated last month
Alternatives and similar repositories for NEO:
Users that are interested in NEO are comparing it to the libraries listed below
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 4 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆40Updated 5 months ago
- ☆12Updated 10 months ago
- Stateful LLM Serving☆63Updated last month
- ☆59Updated 10 months ago
- ☆36Updated 5 months ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆19Updated this week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆34Updated last week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆10Updated 5 months ago
- ☆24Updated last year
- Ultra | Ultimate | Unified CCL☆59Updated 2 months ago
- ☆95Updated 5 months ago
- ☆23Updated 9 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆22Updated 4 months ago
- ☆20Updated 11 months ago
- LLM serving cluster simulator☆97Updated last year
- ☆70Updated 3 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆50Updated 10 months ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆33Updated 10 months ago
- ☆28Updated 10 months ago
- ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 5 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆154Updated 7 months ago
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆42Updated 2 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆36Updated 4 months ago
- ☆58Updated 3 weeks ago
- ☆16Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 11 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 8 months ago