Max Ryabinin
- Papers
- 14
Cite
Notes
Only stored in your browser.
Authored papers
14Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
arXiv 2026
AutoJudge: Judge Decoding Without Manual Annotation
arXiv 2025
Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding
arXiv 2024
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements
arXiv 2024
RedPajama: an Open Dataset for Training Large Language Models
arXiv 2024
SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices
arXiv 2024
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
arXiv 2023
Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy
arXiv 2023
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
swarm-parallelism-training-large-models-can
Petals: Collaborative Inference and Fine-tuning of Large Models
arXiv 2022
RuCoLA: Russian Corpus of Linguistic Acceptability
arXiv 2022
Secure Distributed Training at Scale
secure-distributed-training-at-scale-1
It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning
arXiv 2021
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts
NeurIPS 2020 12
Affiliations
Frequent co-authors
10from 14 papers