timlee0212 / SiDA-MoE
Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"
☆17Updated last year
Alternatives and similar repositories for SiDA-MoE:
Users that are interested in SiDA-MoE are comparing it to the libraries listed below
- Stateful LLM Serving☆65Updated last month
- ☆59Updated 10 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- ☆95Updated 5 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆47Updated 6 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆34Updated last week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆29Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆164Updated 6 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆118Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆155Updated 7 months ago
- A resilient distributed training framework☆95Updated last year
- ☆100Updated 6 months ago
- ☆104Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- ☆24Updated last year
- High performance Transformer implementation in C++.☆120Updated 3 months ago
- ☆20Updated 11 months ago
- LLM Inference analyzer for different hardware platforms☆65Updated last week
- LLM Serving Performance Evaluation Harness☆77Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆109Updated last week
- Dynamic resources changes for multi-dimensional parallelism training☆25Updated 5 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 11 months ago
- ATC23 AE☆45Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year
- ☆23Updated 10 months ago
- An experimental parallel training platform☆54Updated last year
- ☆72Updated 3 years ago
- A lightweight design for computation-communication overlap.☆67Updated last week