flashserve / PATLinks
Prefix-Aware Attention for LLM Decoding
☆25Updated last week
Alternatives and similar repositories for PAT
Users that are interested in PAT are comparing it to the libraries listed below
Sorting:
- Curated collection of papers in machine learning systems☆500Updated last month
- ☆28Updated last week
- This repository is established to store personal notes and annotated papers during daily research.☆179Updated 2 weeks ago
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆40Updated 2 months ago
- Paper reading and discussion notes, covering AI frameworks, distributed systems, cluster management, etc.☆53Updated 2 months ago
- ☆323Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆236Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆772Updated 9 months ago
- A Throughput-Optimized Pipeline Parallel Inference System for Large Language Models☆46Updated last month
- [NSDI25] AutoCCL: Automated Collective Communication Tuning for Accelerating Distributed and Parallel DNN Training☆30Updated 8 months ago
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆154Updated this week
- ☆29Updated last year
- Summary of some awesome work for optimizing LLM inference☆172Updated 2 months ago
- ☆28Updated last year
- ☆15Updated last year
- ☆166Updated last year
- Curated collection of papers in MoE model inference☆339Updated 3 months ago
- ☆14Updated last year
- iGniter, an interference-aware GPU resource provisioning framework for achieving predictable performance of DNN inference in the cloud.☆39Updated last year
- Galvatron is an automatic distributed training system designed for Transformer models, including Large Language Models (LLMs). If you hav…☆23Updated 3 months ago
- A large-scale simulation framework for LLM inference☆528Updated 6 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Updated last year
- ☆803Updated last month
- paper and its code for AI System☆347Updated last month
- LLM serving cluster simulator☆134Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,110Updated last week
- ☆12Updated last year
- ☆21Updated last year
- Modular RDMA Interface☆73Updated this week
- A baseline repository of Auto-Parallelism in Training Neural Networks☆147Updated 3 years ago