sohu-mptc / FlashRecView on GitHub
FlashRec is a CUDA-graph engine for generative recommendation: wide beam search (3–5 SID steps, n=50–512+) over a trie-constrained catalog, in-process FP8 serving, and ranked beams on /v1/chat/completions.
102Sep 8, 2026Updated this week

Alternatives and similar repositories for FlashRec

Users that are interested in FlashRec 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?