eniac / paella
Paella: Low-latency Model Serving with Virtualized GPU Scheduling
☆58Updated 10 months ago
Alternatives and similar repositories for paella:
Users that are interested in paella are comparing it to the libraries listed below
- ☆75Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆93Updated 2 years ago
- High performance Transformer implementation in C++.☆109Updated 2 months ago
- ☆47Updated 2 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆129Updated last month
- ☆23Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 2 years ago
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆37Updated 3 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 7 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated last year
- ☆33Updated 2 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆153Updated 5 months ago
- NCCL Profiling Kit☆127Updated 8 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- An experimental parallel training platform☆54Updated 11 months ago
- nnScaler: Compiling DNN models for Parallel Training☆103Updated last month
- ☆25Updated 11 months ago
- ☆23Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆119Updated 2 years ago
- LLM serving cluster simulator☆94Updated 10 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆143Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127Updated 2 years ago
- SOTA Learning-augmented Systems☆35Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- ☆90Updated 4 months ago
- PilotFish harvests the free GPU cycles of cloud gaming with deep learning training☆13Updated 2 years ago
- ☆69Updated 3 years ago