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:
- ☆99Updated 6 months ago
- Stateful LLM Serving☆70Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆86Updated 2 years ago
- ☆62Updated 11 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆174Updated 7 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- A resilient distributed training framework☆95Updated last year
- ☆30Updated 11 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆32Updated last year
- An experimental parallel training platform☆54Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆24Updated 3 weeks ago
- ☆18Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆41Updated 3 weeks ago
- ☆21Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆46Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆114Updated this week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆158Updated 8 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆121Updated last year
- ☆73Updated 3 years ago
- ☆84Updated 3 years ago
- ☆115Updated 5 months ago
- LLM serving cluster simulator☆102Updated last year
- ☆67Updated 7 months ago
- [ATC '24] Metis: Fast automatic distributed training on heterogeneous GPUs (https://www.usenix.org/conference/atc24/presentation/um)☆26Updated 6 months ago
- ☆25Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆137Updated 4 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆35Updated 3 months ago
- ATC23 AE☆45Updated 2 years ago