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:
- ☆79Updated last month
- Stateful LLM Serving☆88Updated 8 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆31Updated last year
- ☆151Updated 4 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆191Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆64Updated last year
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆62Updated 3 weeks ago
- ☆124Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆98Updated 2 months ago
- ☆140Updated last year
- A resilient distributed training framework☆96Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆131Updated 11 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆259Updated last month
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated 2 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆89Updated 5 months ago
- LLM Serving Performance Evaluation Harness☆80Updated 8 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆15Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93Updated 2 years ago
- A framework for generating realistic LLM serving workloads☆79Updated last month
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated last year
- ☆88Updated 3 years ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆45Updated 8 months ago
- An experimental parallel training platform☆56Updated last year
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆35Updated 2 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆48Updated 3 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- Microsoft Collective Communication Library☆66Updated 11 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆160Updated last year
- Modular and structured prompt caching for low-latency LLM inference☆102Updated last year