alesha-pro / vllm-cross-model-kvView on GitHub
Cross-model KV cache transfer in vLLM: a smaller model prefills, a bigger one answers from its cache (independent implementation of arXiv:2608.03893, measured on 2x RTX 3090)
☆19Aug 10, 2026Updated 2 months ago

Alternatives and similar repositories for vllm-cross-model-kv

Users that are interested in vllm-cross-model-kv 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?