ruipeterpan / marconiLinks
Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
☆15Updated 5 months ago
Alternatives and similar repositories for marconi
Users that are interested in marconi are comparing it to the libraries listed below
Sorting:
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆49Updated last month
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆35Updated last week
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆58Updated 8 months ago
- ☆39Updated last month
- ☆49Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆74Updated 3 years ago
- ☆67Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆147Updated last year
- LLM serving cluster simulator☆108Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆28Updated 2 months ago
- ☆42Updated this week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆21Updated 3 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆96Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆142Updated 6 months ago
- ☆109Updated 8 months ago
- ☆48Updated last month
- Stateful LLM Serving☆77Updated 4 months ago
- ☆83Updated 4 months ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated this week
- High performance Transformer implementation in C++.☆129Updated 6 months ago
- ☆24Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆190Updated last week
- ☆80Updated 2 years ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆74Updated 2 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆42Updated 7 months ago
- ☆24Updated 2 years ago
- ☆13Updated last year