Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
☆73Mar 17, 2026Updated 4 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:
- ☆24Jan 18, 2026Updated 6 months ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆1,131Updated this week
- A language for video analytics☆12Jan 26, 2023Updated 3 years ago
- ☆16May 27, 2026Updated 2 months ago
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆68Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆18Sep 21, 2025Updated 10 months ago
- A framework for generating realistic LLM serving workloads☆168Jul 30, 2026Updated last week
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆47May 13, 2025Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆117Dec 2, 2025Updated 8 months ago
- Generate presentation slides automatically using AI from text, PDFs, or structured content.☆17Mar 17, 2026Updated 4 months ago
- ☆21May 27, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆512Jul 17, 2026Updated 3 weeks ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- ☆32Jan 16, 2025Updated last year
- 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.
- Mako is a low-pause, high-throughput garbage collector designed for memory-disaggregated datacenters.☆15Sep 2, 2024Updated last year
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆17Mar 12, 2026Updated 4 months ago
- Poise source code repo☆12Aug 12, 2020Updated 5 years ago
- ☆135Nov 11, 2024Updated last year
- Sardeenz is a proof-of-concept application that allows you to load more than one model on a given GPU. It allows you to add more and more…☆61Jun 9, 2026Updated 2 months ago
- Synchronizing Claude Code conversations across machines☆16Jul 23, 2026Updated 2 weeks ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 4 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated 3 weeks ago
- SwiftRDMA -- Exposing RDMA NIC Resources for Software-Defined RDMA Scheduling☆53Jun 9, 2026Updated 2 months 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.
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆52Jan 8, 2026Updated 7 months ago
- VQPy: An object-oriented approach to modern video analytics☆42Oct 28, 2024Updated last year
- ☆10Sep 19, 2021Updated 4 years ago
- Efficient and easy multi-instance LLM serving☆564Mar 12, 2026Updated 4 months ago
- ☆16Jun 15, 2026Updated last month
- Agent application/benchmark/workload traces should be placed here.☆15Apr 13, 2026Updated 3 months ago
- ☆13Jan 7, 2025Updated last year
- ☆91Oct 17, 2025Updated 9 months ago
- Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO. I AM NOT ONE OF THE AUTHORS OF THE PAPER.☆67Nov 24, 2025Updated 8 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Large Language Model (LLM) Serving Paper and Resource List☆29Jul 16, 2026Updated 3 weeks ago
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆129Jul 25, 2026Updated 2 weeks ago
- ☆52Dec 19, 2025Updated 7 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆214Mar 18, 2026Updated 4 months ago
- ☆97Sep 15, 2025Updated 10 months ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Aug 6, 2025Updated last year
- ☆160Apr 23, 2026Updated 3 months ago