Multi-LLM / prism-researchLinks
Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
☆46Updated 3 months ago
Alternatives and similar repositories for prism-research
Users that are interested in prism-research are comparing it to the libraries listed below
Sorting:
- Stateful LLM Serving☆89Updated 8 months ago
- ☆79Updated last month
- ☆68Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆63Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- ☆123Updated last year
- High performance Transformer implementation in C++.☆142Updated 10 months ago
- ☆79Updated 3 years ago
- A framework for generating realistic LLM serving workloads☆82Updated last month
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆51Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆220Updated 4 months ago
- ☆61Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆196Updated last year
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆69Updated 5 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆91Updated 2 years ago
- ☆40Updated last year
- ☆90Updated 7 months ago
- ☆152Updated 4 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆82Updated this week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆39Updated 6 months ago
- [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization☆21Updated 3 months ago
- ☆27Updated last year
- Compiler for Dynamic Neural Networks☆46Updated 2 years ago
- DeepSeek-V3/R1 inference performance simulator☆168Updated 8 months ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆48Updated last year
- ☆23Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆64Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆73Updated last month
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆99Updated 2 months ago