hongzhangblaze / CS854-F24
☆20Updated last week
Related projects ⓘ
Alternatives and complementary repositories for CS854-F24
- ☆43Updated last month
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- Systems for GenAI☆67Updated this week
- ☆55Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆126Updated 3 weeks ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- ☆12Updated 6 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆75Updated 4 months ago
- ☆14Updated 5 months ago
- Stateful LLM Serving☆37Updated 3 months ago
- Compiler for Dynamic Neural Networks☆43Updated 11 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- ☆13Updated 3 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆99Updated 8 months ago
- GPU-accelerated vector query processing system that supports large vector datasets beyond GPU memory.☆18Updated 7 months ago
- ☆15Updated 4 months ago
- ☆51Updated 3 years ago
- ☆51Updated last month
- ☆23Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆64Updated 2 weeks ago
- This repository is established to store personal notes and annotated papers during daily research.☆86Updated this week
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆61Updated this week
- LLM serving cluster simulator☆78Updated 6 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆29Updated last year
- ☆82Updated 5 months ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (…☆19Updated 5 months ago
- ☆13Updated 2 years ago
- ☆32Updated last year
- Artifacts for our SIGCOMM'23 paper Ditto☆16Updated last year