Repos
38
Stars
111
Forks
8
Top Language
Python
Loading contributions...
Top Repositories
Heuristic Search vs. Learning. "Distributed Heuristic Multi-Agent Path Finding with Communication" reproduced, trained & benchmarked with M*
Learnable MAPF. “Distributed Heuristic Multi-Agent Path Finding with Communication” (DHC) algorithm from ICRA 2021 is implemented and benchmarked in out-of-distribution (OOD) scenarios. A new robust training loop to handle communication failures is introduced.
Materials for the "Speeding up training with Triton and FP8" which were used for the https://llmscaling.yandex.com/en.
Algo trading strategy, entrance task to CMF, Quantitative Analytics program, 2021
My public talks are presented here
Kaggle classification contest report (in Russian)
Repositories
38No description provided.
Learnable MAPF. “Distributed Heuristic Multi-Agent Path Finding with Communication” (DHC) algorithm from ICRA 2021 is implemented and benchmarked in out-of-distribution (OOD) scenarios. A new robust training loop to handle communication failures is introduced.
Heuristic Search vs. Learning. "Distributed Heuristic Multi-Agent Path Finding with Communication" reproduced, trained & benchmarked with M*
Materials for the "Speeding up training with Triton and FP8" which were used for the https://llmscaling.yandex.com/en.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Offline to Online RL: AWAC & IQL PyTorch Implementation
Tile primitives for speedy kernels
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
This repo contain the syllabus of the Hugging Face Deep Reinforcement Learning Class.
Lab Materials for MIT 6.S191: Introduction to Deep Learning
NanoGPT (124M) quality in 7.8 8xH100-minutes
No description provided.
Algo trading strategy, entrance task to CMF, Quantitative Analytics program, 2021
🎓 Hugo Academic Theme 创建一个学术网站. Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify.
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Large Language Model Text Generation Inference
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
My public talks are presented here
PyTorch implementation of the original transformer, from scratch
Distributed Heuristic Multi-Agent Path Finding with Communication - ICRA 2021
Optax is a gradient processing and optimization library for JAX.
Pipeline Parallelism for PyTorch
Gradient Descent Homework for the ML Course @ SPbU
Kaggle classification contest report (in Russian)
LeetCode solutions
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
No description provided.
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
Decision Tree Implementation as a part of my ML hw @ SPbU