Nerif-AI / NerifLinks
LLM-powered Python
☆15Updated 6 months ago
Alternatives and similar repositories for Nerif
Users that are interested in Nerif are comparing it to the libraries listed below
Sorting:
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆209Updated last year
- ☆342Updated 2 weeks ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆283Updated 11 months ago
- paper and its code for AI System☆347Updated last month
- Serverless LLM Serving for Everyone.☆647Updated 2 weeks ago
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆155Updated 2 weeks ago
- A large-scale simulation framework for LLM inference☆530Updated 6 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆279Updated last week
- Fast OS-level support for GPU checkpoint and restore☆271Updated 4 months ago
- A framework for generating realistic LLM serving workloads☆100Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆93Updated 2 years ago
- LLM checkpointing for DeepSpeed/Megatron☆24Updated 2 months ago
- High performance Transformer implementation in C++.☆151Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆71Updated 4 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆462Updated this week
- This repository is established to store personal notes and annotated papers during daily research.☆180Updated 3 weeks ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆82Updated last year
- torchcomms: a modern PyTorch communications API☆330Updated this week
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆34Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆458Updated 8 months ago
- Venus Collective Communication Library, supported by SII and Infrawaves.☆137Updated last week
- ☆85Updated 3 months ago
- Thunder Research Group's Collective Communication Library☆47Updated 7 months ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆57Updated 5 months ago
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆112Updated last month
- Stateful LLM Serving☆95Updated 11 months ago
- A lightweight design for computation-communication overlap.☆219Updated 3 weeks ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆135Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆63Updated 6 months ago
- Dynamic resources changes for multi-dimensional parallelism training☆30Updated 5 months ago