UofT-EcoSystem / hotlineLinks
☆32Updated 2 years ago
Alternatives and similar repositories for hotline
Users that are interested in hotline are comparing it to the libraries listed below
Sorting:
- ☆79Updated 2 years ago
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆121Updated 3 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- ☆75Updated 4 years ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆144Updated 3 years ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated 2 years ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆50Updated 11 months ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆20Updated 2 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆40Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 2 months ago
- System for automated integration of deep learning backends.☆47Updated 2 years ago
- A tool for examining GPU scheduling behavior.☆84Updated 10 months ago
- DietCode Code Release☆64Updated 2 years ago
- A home for the final text of all TVM RFCs.☆105Updated 9 months ago
- ☆145Updated 5 months ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- High performance NCCL plugin for Bagua.☆15Updated 3 years ago
- An Efficient Pipelined Data Parallel Approach for Training Large Model☆77Updated 4 years ago
- ☆94Updated 6 months ago
- A lightweight design for computation-communication overlap.☆146Updated 3 weeks ago
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated last year
- Thunder Research Group's Collective Communication Library☆38Updated last week
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 10 months ago
- Model-less Inference Serving☆88Updated last year
- Analysis for the traces from byteprofile☆32Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆50Updated 2 years ago
- HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of…☆156Updated 2 weeks ago