Why does vLLM 0.30.0 cut some models' max context length?
vLLM 0.30.0, released September 22, 2026, fixed a bug where vendor YaRN aliases like deepseek_yarn and telechat3-yarn double-applied the scaling factor, PR #56446. TeleChat3-36B-Thinking's derived max_model_len drops from 131072 to 32768, sarvam-105b's from 5242880 to 131072, both exactly 4x and 40x, and the old, larger figures risked indexing past the cache.
3 min read