# xAI rewrites RL and inference stack in C/C++ for Grok 4.8

> Original title: Grok 4.8 就在眼前。

- Source: Dongxi NLP
- Published: 2026-11-10T13:06:06.000Z
- Bad Influence: https://badinfluence.news/items/ug1hadh9obxquqe4i7d1n4ors
- Original: https://x.com/dongxi_nlp/status/2120140944704160196

## Summary

Elon Musk says xAI dumped JAX and SGLang and rewrote its entire RL and inference stack from scratch in C/C++. Pre-training for Grok 4.8 is finished and the model is now in RL, with evals starting to climb. A soft rollout to Bot users is planned for later this week.

## Post

Grok 4.8 就在眼前。

SpaceX AI 的 RL 和 inference infra 全部重写。

马斯克对训练技术细节描述的太准确了，像是一名专业的模型训练人员说的话。在这样的老板手下干活，啥鱼也别想摸了咱们这边就是说。

## Quoted post @elonmusk

> We have dumped JAX/SGLang and rewritten the entire RL and inference stack from scratch in C/C++, which took some extra time. 
> 
> Training (aka pre-training) is done. Lot of cleanup was needed on the SFT data to get that mostly right. Now, 4.8 is in RL and the evals are starting to climb. We will do a soft rollout to Bot users later this week and see how it goes.
> 
> Grok 4.8 will bear no resemblance to 4.7 (thankfully). It is not yet incredible, but, this time, the foundations are built right, so I expect it to evolve to be something special.

https://x.com/elonmusk/status/2120088070443655190