hao-ai-lab / MuxServeLinks
☆69Updated last year
Alternatives and similar repositories for MuxServe
Users that are interested in MuxServe are comparing it to the libraries listed below
Sorting:
- ☆120Updated 10 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- Stateful LLM Serving☆81Updated 6 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆86Updated this week
- A lightweight design for computation-communication overlap.☆161Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆181Updated 11 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆219Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆56Updated last week
- ☆133Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 10 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆29Updated last year
- A resilient distributed training framework☆94Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated last year
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Microsoft Collective Communication Library☆66Updated 9 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆231Updated 2 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆152Updated last year
- ☆126Updated 11 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆70Updated 3 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆66Updated 5 months ago
- A framework for generating realistic LLM serving workloads☆55Updated 3 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆58Updated last week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆60Updated this week
- ☆150Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆203Updated last month
- Explore Inter-layer Expert Affinity in MoE Model Inference☆13Updated last year