timlee0212 / SiDA-MoELinks
Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"
☆18Updated 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:
- Stateful LLM Serving☆73Updated 3 months ago
- ☆62Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆26Updated last year
- ☆103Updated 7 months ago
- An experimental parallel training platform☆54Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆177Updated 8 months ago
- ☆74Updated 4 years ago
- LLM serving cluster simulator☆106Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆42Updated last month
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆52Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆163Updated 9 months ago
- A resilient distributed training framework☆95Updated last year
- ☆72Updated 3 years ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆34Updated last year
- A lightweight design for computation-communication overlap.☆143Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- Dynamic resources changes for multi-dimensional parallelism training☆25Updated 7 months ago
- ☆21Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆54Updated 2 weeks ago
- ☆121Updated 5 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ☆32Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last week
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆39Updated last week
- ☆109Updated 8 months ago
- ☆18Updated last year