NEO-MLSys25 / NEOLinks
NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
☆36Updated 3 months ago
Alternatives and similar repositories for NEO
Users that are interested in NEO are comparing it to the libraries listed below
Sorting:
- Stateful LLM Serving☆70Updated 2 months ago
- ☆62Updated 11 months ago
- Ultra | Ultimate | Unified CCL☆102Updated this week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Honorable Mention]☆10Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆174Updated 7 months ago
- ☆99Updated 6 months ago
- LLM serving cluster simulator☆102Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- High performance Transformer implementation in C++.☆124Updated 4 months ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆35Updated last year
- ☆119Updated 5 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆121Updated last year
- ☆25Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆41Updated 3 weeks ago
- ☆30Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆46Updated 6 months ago
- LLM Inference analyzer for different hardware platforms☆72Updated last week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆23Updated 3 weeks ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- ☆37Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆158Updated 8 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆137Updated 4 months ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 3 weeks ago
- A resilient distributed training framework☆95Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆12Updated last month
- ☆23Updated 11 months ago
- A lightweight design for computation-communication overlap.☆136Updated this week
- ☆21Updated last year
- ☆53Updated 4 years ago