tonyzhao-jt / LLM-PQ
Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"
☆27Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for LLM-PQ
- ☆46Updated 5 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆132Updated last month
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆15Updated 6 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- ☆52Updated last week
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated last year
- A resilient distributed training framework☆85Updated 7 months ago
- ☆23Updated last year
- ☆42Updated 7 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- Stateful LLM Serving☆38Updated 3 months ago
- ☆66Updated last month
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated 8 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- LLM Inference analyzer for different hardware platforms☆42Updated this week
- ☆15Updated 4 months ago
- LLM serving cluster simulator☆81Updated 6 months ago
- ☆14Updated 5 months ago
- ☆35Updated 3 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 3 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆34Updated 2 years ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- ☆70Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- ☆65Updated 3 years ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (…☆22Updated 5 months ago
- ☆51Updated last month
- ☆41Updated 2 years ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 8 months ago
- ☆95Updated 10 months ago