AlibabaPAI / llumnix
Efficient and easy multi-instance LLM serving
☆213Updated this week
Related projects ⓘ
Alternatives and complementary repositories for llumnix
- A low-latency & high-throughput serving engine for LLMs☆245Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆238Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆359Updated 3 months ago
- Ultra-Fast and Cheaper Long-Context LLM Inference☆233Updated this week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆175Updated 2 weeks ago
- High performance Transformer implementation in C++.☆82Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 8 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆57Updated 6 months ago
- A large-scale simulation framework for LLM inference☆277Updated last month
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆311Updated 2 months ago
- ☆52Updated last week
- paper and its code for AI System☆215Updated 2 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆114Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆110Updated 6 months ago
- A fast communication-overlapping library for tensor parallelism on GPUs.☆224Updated 3 weeks ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆132Updated last month
- Materials for learning SGLang☆96Updated this week
- nnScaler: Compiling DNN models for Parallel Training☆74Updated 3 weeks ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆75Updated this week
- ☆51Updated last month
- GLake: optimizing GPU memory management and IO transmission.☆379Updated 3 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆250Updated this week
- A resilient distributed training framework☆85Updated 7 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- Summary of some awesome work for optimizing LLM inference☆37Updated 2 weeks ago
- Curated collection of papers in machine learning systems☆163Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆180Updated last year
- Zero Bubble Pipeline Parallelism☆281Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago