mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-27 08:27:30 -05:00
* add lru_sched * handle coalescing (req leaves waiting queue) * add tests * fix stream case * address review comments
* add lru_sched * handle coalescing (req leaves waiting queue) * add tests * fix stream case * address review comments