pie-project / pieLinks
Pie: Programmable LLM Serving
☆42Updated last week
Alternatives and similar repositories for pie
Users that are interested in pie are comparing it to the libraries listed below
Sorting:
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated 2 months ago
- ☆12Updated 6 months ago
- ☆25Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆34Updated 5 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- ☆56Updated 4 months ago
- A Progam-Behavior-Guided Far Memory System☆35Updated 2 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43Updated 3 years ago
- Deduplication over dis-aggregated memory for Serverless Computing☆14Updated 3 years ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆101Updated 2 years ago
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆129Updated last week
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆68Updated 2 weeks ago
- ☆53Updated 10 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 11 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆67Updated 4 months ago
- Tigon: A Distributed Database for a CXL Pod [OSDI '25]☆36Updated 4 months ago
- [USENIX ATC 2021] Exploring the Design Space of Page Management for Multi-Tiered Memory Systems☆47Updated 3 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- ☆24Updated 3 years ago
- Vector search with bounded performance.☆36Updated last year
- ☆24Updated 2 weeks ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 11 months ago
- SOTA Learning-augmented Systems☆37Updated 3 years ago
- LLM serving cluster simulator☆116Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- Artifact evaluation repo for EuroSys'24.☆28Updated last year
- ☆27Updated last year
- Artifacts of EuroSys'24 paper "Exploring Performance and Cost Optimization with ASIC-Based CXL Memory"☆29Updated last year