verl (HybridFlow)
by verl project (originated at ByteDance Seed)
Explore how an RL training framework coordinates generation and optimization.
The verl project exposes a modular approach to post-training dataflows and distributed model execution. Its documentation is most useful to readers who already understand training loops and need to reason about infrastructure trade-offs.
- Level
- Expert
- Models
- any
- Category
- Model Training
- Tags
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- Acts on model-training, infrastructure or research tooling; requires training-stack expertise.
- Subcategory
- post training rl
- Region
- CN
- Original language
- en
- Access
- free
- Resource reuse
- open: Source states Apache-2.0. Applies to the linked resource, not every referenced model or dataset. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.