microsoft / ParrotServeLinks
[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
☆163Updated 9 months ago
Alternatives and similar repositories for ParrotServe
Users that are interested in ParrotServe are comparing it to the libraries listed below
Sorting:
- Stateful LLM Serving☆73Updated 3 months ago
- ☆62Updated last year
- ☆103Updated 7 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆123Updated last year
- ☆121Updated 5 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆255Updated 3 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last week
- ☆109Updated 8 months ago
- A resilient distributed training framework☆95Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆177Updated 8 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆42Updated last month
- ☆72Updated 3 years ago
- Modular and structured prompt caching for low-latency LLM inference☆96Updated 7 months ago
- LLM Serving Performance Evaluation Harness☆78Updated 4 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆26Updated last year
- A lightweight design for computation-communication overlap.☆143Updated this week
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆25Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆198Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆224Updated 2 weeks ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆39Updated last week
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆52Updated last week
- ☆47Updated last year
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 7 months ago
- Summary of some awesome work for optimizing LLM inference☆77Updated 3 weeks ago
- LLM serving cluster simulator☆106Updated last year