Skip to content
View dvmazur's full-sized avatar
🍋
🍋

Block or report dvmazur

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. yandexdataschool/Practical_DL Public

    DL course co-developed by YSDA, HSE and Skoltech

    Jupyter Notebook 1.6k 647

  2. learning-at-home/hivemind Public

    Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

    Python 2.2k 183

  3. mixtral-offloading Public

    Run Mixtral-8x7B models in Colab or consumer desktops

    Python 2.3k 233

  4. Vahe1994/AQLM Public

    Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Ext…

    Python 1.2k 181

39 contributions in the last year

Contribution Graph
Day of Week April May June July August September October November December January February March April
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Activity overview

Contributed to learning-at-home/hivemind, pytorch/tensordict, dvmazur/AQLM and 5 other repositories
Loading A graph representing dvmazur's contributions from April 21, 2024 to April 22, 2025. The contributions are 61% commits, 21% pull requests, 12% code review, 6% issues.

Contribution activity

April 2025

Created an issue in volcengine/verl that received 10 comments

Add asynchronous rollout + reward stage to PPOTrainer

When training on code tasks, the reward stage can take quite a long time, as it requires compiling the model's output and running quite a lot of te…

10 comments
Loading