Hsword / SpotServe
SpotServe: Serving Generative Large Language Models on Preemptible Instances
☆92Updated 6 months ago
Related projects: ⓘ
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- A resilient distributed training framework☆78Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆119Updated this week
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆76Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆92Updated 4 months ago
- A low-latency & high-throughput serving engine for LLMs☆174Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆54Updated 3 months ago
- ☆15Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆89Updated last week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆153Updated this week
- LLM serving cluster simulator☆55Updated 4 months ago
- ☆12Updated 2 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- ☆30Updated this week
- Efficient serverless deployment for large AI models.☆178Updated this week
- ☆12Updated 3 months ago
- Curated collection of papers in machine learning systems☆123Updated last month
- ☆49Updated 2 years ago
- ☆47Updated 3 weeks ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆38Updated 3 weeks ago
- Stateful LLM Serving☆25Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆55Updated 4 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆124Updated 2 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- Compiler for Dynamic Neural Networks☆42Updated 10 months ago
- ☆30Updated 3 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆14Updated 4 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 4 months ago
- An experimental parallel training platform☆46Updated 5 months ago
- ☆33Updated 2 weeks ago