timlee0212 / SiDA-MoELinks
Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"
☆22Updated 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:
- ☆83Updated 3 months ago
- ☆131Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆34Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆232Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- Stateful LLM Serving☆95Updated 10 months ago
- A resilient distributed training framework☆96Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆92Updated 2 years ago
- ☆79Updated 3 years ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Updated 2 years ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Updated last month
- A framework for generating realistic LLM serving workloads☆98Updated 3 months ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆36Updated 5 months ago
- ☆147Updated last year
- ☆164Updated 6 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆67Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆207Updated last year
- ☆29Updated last year
- ☆43Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆159Updated 2 months ago
- A lightweight design for computation-communication overlap.☆213Updated last week
- High performance Transformer implementation in C++.☆148Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆119Updated 3 weeks ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆76Updated 3 months ago
- LLM serving cluster simulator☆132Updated last year
- This repository is established to store personal notes and annotated papers during daily research.☆175Updated last week
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- Compiler for Dynamic Neural Networks☆45Updated 2 years ago