microsoft / vidurLinks
A large-scale simulation framework for LLM inference
☆500Updated 4 months ago
Alternatives and similar repositories for vidur
Users that are interested in vidur are comparing it to the libraries listed below
Sorting:
- A low-latency & high-throughput serving engine for LLMs☆456Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆517Updated 3 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆754Updated 8 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆448Updated 6 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆226Updated 4 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆467Updated 8 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆599Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆265Updated 2 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…☆282Updated 9 months ago
- paper and its code for AI System☆341Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆300Updated 6 months ago
- ☆144Updated last year
- This repository is established to store personal notes and annotated papers during daily research.☆169Updated this week
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆141Updated last month
- ☆126Updated last year
- Curated collection of papers in machine learning systems☆479Updated last week
- LLM serving cluster simulator☆127Updated last year
- ☆612Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆203Updated last year
- ☆332Updated this week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆133Updated last year
- ☆79Updated 2 months ago
- DeepSeek-V3/R1 inference performance simulator☆172Updated 8 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆154Updated 3 weeks ago
- High performance Transformer implementation in C++.☆146Updated 11 months ago
- Stateful LLM Serving☆90Updated 9 months ago
- ☆156Updated 5 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆167Updated last year
- Perplexity GPU Kernels☆539Updated last month
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆92Updated 2 years ago