MiMo-V2.5-Pro-FP4

Headlines · 1

1. 6d
   vLLM Adaptive Verification works without a confidence head via online estimator

   A vLLM blog post says Adaptive Verification previously required a per-token acceptance estimate, so it only supported DSpark drafters that ship with a confidence head, leaving EAGLE, MTP, DFlash and some DSpark checkpoints unable to use the optimization. The new approach, when no confidence head exists, derives a feature from the log-odds of the drafter's most likely token and fits a lightweight logistic regression online, with one shared slope and one intercept per draft position, continuously updated from the target model's accept/reject decisions. The feature landed in PR #52228 and is enabled with enable_adaptive_verification for draft models without a confidence head, with results reported for DeepSeek-V4-Flash + DSpark and MiMo-V2.5-Pro-FP4 + DFlash.

   vLLM Blog · 🔥 0

Experience and discussion from the community

Share my MiMo-V2.5-Pro-FP4 experienceAsk about MiMo-V2.5-Pro-FP4