Hsword / SpotServe
SpotServe: Serving Generative Large Language Models on Preemptible Instances
☆101Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for SpotServe
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆132Updated last month
- ☆52Updated last week
- ☆46Updated 5 months ago
- A resilient distributed training framework☆85Updated 7 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆110Updated 6 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- Stateful LLM Serving☆38Updated 3 months ago
- ☆51Updated last month
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆213Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆114Updated 2 months ago
- An experimental parallel training platform☆52Updated 7 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆175Updated 2 weeks ago
- LLM serving cluster simulator☆81Updated 6 months ago
- paper and its code for AI System☆215Updated 2 months ago
- ☆56Updated 2 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆74Updated 3 weeks ago
- ☆66Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆57Updated 6 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆124Updated 2 years ago
- A low-latency & high-throughput serving engine for LLMs☆245Updated 2 months ago
- ☆14Updated 5 months ago
- Compiler for Dynamic Neural Networks☆43Updated last year
- Ultra-Fast and Cheaper Long-Context LLM Inference☆233Updated this week
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆50Updated 2 months ago
- High performance Transformer implementation in C++.☆82Updated 2 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆79Updated 4 months ago