alibaba / ServeGenLinks
A framework for generating realistic LLM serving workloads
☆76Updated last month
Alternatives and similar repositories for ServeGen
Users that are interested in ServeGen are comparing it to the libraries listed below
Sorting:
- Stateful LLM Serving☆88Updated 8 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- ☆75Updated 3 weeks ago
- A resilient distributed training framework☆96Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆218Updated 3 months ago
- ☆124Updated last year
- ☆27Updated last year
- ☆57Updated 2 weeks ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆89Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆150Updated 9 months ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆47Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆69Updated 3 weeks ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆190Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆48Updated 3 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆68Updated 4 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆31Updated last year
- ☆150Updated 3 months ago
- ☆79Updated 3 years ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆98Updated last month
- ☆38Updated last year
- ☆139Updated last year
- ☆64Updated last month
- ☆56Updated 4 years ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 11 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆131Updated last week
- Dynamic resources changes for multi-dimensional parallelism training☆29Updated 2 months ago
- ☆21Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆36Updated 5 months ago