timlee0212 / SiDA-MoELinks
Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"
☆21Updated last year
Alternatives and similar repositories for SiDA-MoE
Users that are interested in SiDA-MoE are comparing it to the libraries listed below
Sorting:
- ☆71Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- A resilient distributed training framework☆95Updated last year
- Stateful LLM Serving☆85Updated 6 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆183Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 10 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- ☆137Updated 2 months ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆34Updated 3 weeks ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆58Updated last week
- ☆87Updated 3 years ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆93Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- ☆123Updated 10 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆32Updated 6 months ago
- A framework for generating realistic LLM serving workloads☆63Updated 3 months ago
- LLM checkpointing for DeepSpeed/Megatron☆20Updated 2 weeks ago
- ☆130Updated 11 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆85Updated 2 years ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆24Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆81Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated 3 weeks ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆154Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆238Updated 2 months ago
- ATC23 AE☆47Updated 2 years ago
- Dynamic resources changes for multi-dimensional parallelism training☆27Updated last month
- A lightweight design for computation-communication overlap.☆171Updated last week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆205Updated 2 months ago