b9273

Release b9273 of llama.cpp introduces support for the HybridDNATokenizer with new pre-type and dispatched tokenization logic, alongside pure helper functions for DNA k-mer processing and conversion utilities for detecting and loading custom tokenizer classes. The release also fixes a critical VRAM memory leak in the server context by properly cleaning up speculative decoder, draft context, and draft model resources during the destroy function, preventing out-of-memory crashes on sleep/resume cycles in Multi-Token Prediction models.

Source: llama.cpp Releases | 2026-05-21