精选理由
PrimeIntellect发了Verifiers v1，用vLLM做强化学习rollout，token精度更高，训练更稳定。搞开源RL的可以看看。
PrimeIntellect推出Verifiers v1，使用vLLM进行训练rollouts，确保精确的token IDs和logprobs。该方法消除了tokenization漂移，使rollouts与训练保持同步。vLLM还支持开源RL基础设施如prime-rl。这一发布提升了强化学习训练的稳定性和效率。
原文 · vLLM
🎉 Congrats to @PrimeIntellect on Verifiers v1! Its…
🎉 Congrats to @PrimeIntellect on Verifiers v1! Its training rollouts run on vLLM for exact token IDs and logprobs, no tokenization drift, keeping rollouts and training in sync.
vLLM powers a growing set of open RL infra, prime-rl and others, and it's an area we're going deep on. 🚀