tonyzhao-jt / LLM-PQ
Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"
☆29Updated last year
Alternatives and similar repositories for LLM-PQ:
Users that are interested in LLM-PQ are comparing it to the libraries listed below
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- ☆59Updated 10 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- A resilient distributed training framework☆95Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆40Updated 5 months ago
- ☆24Updated last year
- Stateful LLM Serving☆65Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆47Updated 6 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆155Updated 7 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆118Updated last year
- ☆53Updated last year
- LLM serving cluster simulator☆99Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 11 months ago
- A lightweight design for computation-communication overlap.☆67Updated last week
- ☆100Updated 6 months ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆164Updated 6 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆11Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 8 months ago
- ☆17Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- LLM Inference analyzer for different hardware platforms☆65Updated last week
- ☆10Updated 3 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 11 months ago
- ☆16Updated 11 months ago
- Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"☆17Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year