hao-ai-lab / MuxServeLinks
☆62Updated 11 months ago
Alternatives and similar repositories for MuxServe
Users that are interested in MuxServe are comparing it to the libraries listed below
Sorting:
- ☆99Updated 6 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆121Updated last year
- Stateful LLM Serving☆70Updated 2 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆157Updated 8 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆171Updated 7 months ago
- A lightweight design for computation-communication overlap.☆131Updated 3 weeks ago
- High performance Transformer implementation in C++.☆123Updated 4 months ago
- ☆111Updated 5 months ago
- LLM serving cluster simulator☆100Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆39Updated 3 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated 11 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- A resilient distributed training framework☆95Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆18Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 6 months ago
- ☆105Updated 7 months ago
- ☆73Updated 4 years ago
- ☆145Updated 10 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Honorable Mention]☆10Updated 2 months ago
- Microsoft Collective Communication Library☆65Updated 6 months ago
- ☆54Updated last year
- ☆13Updated 11 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆134Updated 10 months ago
- Ultra | Ultimate | Unified CCL☆75Updated last week
- Dynamic resources changes for multi-dimensional parallelism training☆25Updated 6 months ago
- ☆79Updated 2 years ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆63Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆86Updated 2 years ago