jelllott / speechkv-trimView on GitHub
Speech-aware KV cache pruning for long-form speech LLMs (Qwen2-Audio, SALMONN). Token/head/chunk-level pruners + eval on LibriSpeech-long & GigaSpeech.
137May 24, 2026Updated last week

Alternatives and similar repositories for speechkv-trim

Users that are interested in speechkv-trim are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?