DeepScaler
BTR ACTIVE BREAKOUT
Democratizing Reinforcement Learning for LLMs
- agent-framework
- agentic-workflow
- distributed-training
- llm-training
- machine-learning
- ml-infrastructure
stars 6k
last activity yesterday
open issues 78
language Python
license Apache-2.0
latest release v0.3.0-pre
momentum · per month since covered + 251/mo
(+17%/mo) · + 4k total since PR#2
metrics as of today
star history
Exact curve on star-history.com ↗- PR#2 2k★ 2025-02-19
- now 6k★ + 4k since first covered
curve is sampled from GitHub's star history; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
covered in
-
Democratizing Reinforcement Learning for LLMs
// comments
COMING SOONSign in with GitHub to weigh in on DeepScaler. We're wiring this up; check back soon.