tonyzhao-jt / LLM-PQ
Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"
☆28Updated 11 months ago
Alternatives and similar repositories for LLM-PQ:
Users that are interested in LLM-PQ are comparing it to the libraries listed below
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆20Updated 9 months ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- A resilient distributed training framework☆88Updated 10 months ago
- ☆50Updated 8 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆39Updated 3 months ago
- LLM serving cluster simulator☆92Updated 9 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆81Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- LLM Inference analyzer for different hardware platforms☆52Updated 3 weeks ago
- ☆24Updated last year
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated 11 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆112Updated 11 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆18Updated 2 months ago
- ☆52Updated 10 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆145Updated 4 months ago
- ☆83Updated 3 months ago
- [IJCAI2023] An automated parallel training system that combines the advantages from both data and model parallelism. If you have any inte…☆51Updated last year
- ☆18Updated 7 months ago
- Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines.☆57Updated last year
- Stateful LLM Serving☆46Updated 6 months ago
- ☆16Updated 8 months ago
- ☆14Updated 9 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆7Updated 9 months ago
- Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"☆15Updated 10 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆46Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆145Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆93Updated last week
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated 9 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆22Updated 3 months ago