# vLLM adds Day-0 reinforcement learning support with Megatron for Kimi Delta Attention

> Original title: Day-0 RL support, too: vLLM + Megatron.

- Source: vLLM
- Published: 2026-11-04T16:08:00.000Z
- Bad Influence: https://badinfluence.news/items/a0g0e7oi0g5vurldw7dmvvs66
- Original: https://x.com/vllm_project/status/2118012395444662444

## Summary

vLLM says it has Day-0 reinforcement learning support through its integration with Megatron. Inferact's work covers training–inference consistency for Kimi Delta Attention, along with cache and state management for serving long-running agents.

## Post

Day-0 RL support, too: vLLM + Megatron.

@inferact’s work covers training–inference consistency for Kimi Delta Attention, alongside the cache and state management needed to serve long-running agents.

From serving the model to continuing its training, the open stack is ready for the next step.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWSxDOpa4AAXG3X.jpg&mode=thumb&exp=1794009600&sig=272b9ede1da75161)