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:
- ☆74Updated 2 weeks ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆188Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆34Updated 2 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆61Updated 11 months ago
- Stateful LLM Serving☆87Updated 7 months ago
- LLM checkpointing for DeepSpeed/Megatron☆21Updated 2 weeks ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆92Updated 2 years ago
- ☆124Updated 11 months ago
- A resilient distributed training framework☆96Updated last year
- ☆144Updated 3 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆94Updated last month
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆130Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆252Updated 2 weeks ago
- ☆136Updated last year
- A framework for generating realistic LLM serving workloads☆73Updated 3 weeks ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆26Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆81Updated 4 months ago
- Modular and structured prompt caching for low-latency LLM inference☆101Updated 11 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated last month
- ATC23 AE☆47Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆48Updated 2 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆14Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆48Updated 2 months ago
- ☆87Updated 3 years ago
- nnScaler: Compiling DNN models for Parallel Training☆117Updated last month
- ☆47Updated last year
- LLM Serving Performance Evaluation Harness☆79Updated 8 months ago
- ☆35Updated last year
- Dynamic resources changes for multi-dimensional parallelism training☆29Updated 2 months ago