Dev Radar
Support
LiveUpdated 2026-09-19 18:39 UTC

You can now do RL weight sync over HF Buckets.

You can now do RL weight sync over HF Buckets. > Async GRPO + LoRA in TRL > train on one Job, serve vLLM on others >…

This is a dev post classified by Jev as Hosting & infra (a launch), kept by the Dev Radar because it carries real work, not commentary.

You can now do RL weight sync over HF Buckets. > Async GRPO + LoRA in TRL > train on one Job, serve vLLM on others > sync just the small delta adapter through a Bucket. Trainer, inference and storage, all on @huggingface infra. Beautifully optimised loop by @DirhoussssiAmine 👇 3h27 → 53 min for the same reward.

Posted by Adithya S K (14.9k followers) 1 days ago · 275 likes · 17.2k views · view the original post on X. Kept by the Dev Radar as Hosting & infra.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.