pie-project / pieLinks
Pie: Programmable LLM Serving
☆121Updated this week
Alternatives and similar repositories for pie
Users that are interested in pie 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☆84Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆209Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆135Updated last year
- ☆16Updated 9 months ago
- Stateful LLM Serving☆95Updated 10 months ago
- ☆80Updated 2 weeks ago
- ☆26Updated 2 years ago
- A resilient distributed training framework☆96Updated last year
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆36Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41Updated 8 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- Accepted to MLSys 2026☆70Updated last week
- A framework for generating realistic LLM serving workloads☆99Updated 4 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆58Updated last year
- ☆43Updated last year
- ☆84Updated 3 months ago
- SOTA Learning-augmented Systems☆37Updated 3 years ago
- Microsoft Collective Communication Library☆66Updated last year
- ☆73Updated 4 months ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Updated 6 months ago
- ☆79Updated 3 years ago
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆62Updated 6 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆104Updated 3 years ago
- ☆95Updated 10 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆55Updated 3 years ago
- ☆51Updated 9 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆93Updated 2 years ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆57Updated 5 months ago
- ☆56Updated 5 years ago