llama : fix defrag bugs + add parameter (#5735)
* llama : fix defrag bugs + enable by default ggml-ci * llama : add defrag_thold parameter ggml-ci * llama : cont * llama : disable log message ggml-ci * llama : fix graph size check during defrag
G
Georgi Gerganov committed
9d533a77d0c3850ce09d736bc1baa67fd6ad27b3
Parent: cbbd1ef
Committed by GitHub <noreply@github.com>
on 2/27/2024, 12:35:51 PM