Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
☆69Mar 17, 2026Updated 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Mako is a low-pause, high-throughput garbage collector designed for memory-disaggregated datacenters.☆15Sep 2, 2024Updated last year
- A language for video analytics☆12Jan 26, 2023Updated 3 years ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆1,077Jun 12, 2026Updated 2 weeks ago
- ☆10Sep 19, 2021Updated 4 years ago
- MemLiner is a remote-memory-friendly runtime system.☆31Nov 1, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A framework for generating realistic LLM serving workloads☆157May 11, 2026Updated last month
- ☆21May 27, 2025Updated last year
- ☆48Dec 19, 2025Updated 6 months ago
- Midas is a memory management system that efficiently and safely harvests idle memory for applications' soft state.☆11Oct 30, 2024Updated last year
- Prefix-Aware Attention for LLM Decoding☆40May 26, 2026Updated last month
- This is the proof-of-concept CPU implementation of ASPEN used for the NeurIPS'23 paper ASPEN: Breaking Operator Barriers for Efficient Pa…☆13Apr 4, 2024Updated 2 years ago
- VQPy: An object-oriented approach to modern video analytics☆42Oct 28, 2024Updated last year
- Dorylus: Affordable, Scalable, and Accurate GNN Training☆76May 31, 2021Updated 5 years ago
- Poise source code repo☆12Aug 12, 2020Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- An Open-Source RAG Workload Trace to Optimize RAG Serving Systems☆37Nov 18, 2025Updated 7 months ago
- ☆15Feb 16, 2022Updated 4 years ago
- 📜 [NeurIPS 2022] "Symbolic Distillation for Learned TCP Congestion Control", S P Sharan, Wenqing Zheng, Kuo-Feng Hsu, Jiarong Xing, Ang …☆16Oct 13, 2022Updated 3 years ago
- ☆54Oct 10, 2024Updated last year
- ☆16Jul 9, 2024Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆54Dec 11, 2022Updated 3 years ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆59Oct 11, 2025Updated 8 months ago
- ☆103May 29, 2026Updated last month
- ☆31Apr 8, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Ch…☆29Jul 15, 2025Updated 11 months ago
- CSS-LM: Contrastive Semi-supervised Fine-tuning of Pre-trained Language Models☆12Jul 1, 2023Updated 3 years ago
- This is the repo for remote direct memory introspection.☆25Jun 21, 2023Updated 3 years ago
- A Memory-Disaggregated Managed Runtime.☆67Aug 28, 2021Updated 4 years ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆111Dec 17, 2025Updated 6 months ago
- *flow source code☆23Aug 27, 2020Updated 5 years ago
- ☆19Feb 14, 2023Updated 3 years ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Feb 29, 2024Updated 2 years ago
- zTT: Learning-based DVFS with Zero Thermal Throttling for Mobile Devices [MobiSys'21] - Artifact Evaluation☆31May 10, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ACL'25 Findings] Official repo for "HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation Task"☆41Apr 7, 2025Updated last year
- ☆41Jan 10, 2026Updated 5 months ago
- ☆36Jan 21, 2021Updated 5 years ago
- An EinSum system in JAX☆41Mar 6, 2026Updated 3 months ago
- ☆13Jul 18, 2024Updated last year
- Memtier benchmark front-end☆10May 9, 2023Updated 3 years ago
- ☆47Sep 8, 2025Updated 9 months ago