mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-01 09:01:57 +00:00
* metal: concurrently dispatch commands Function `ggml_metal_graph_find_concurrency` will run and write commands that can be issued concurrently to metal context `concur_list` array, when `ggml_metal_graph_compute` is called for the first time. * metal: don't call find_concurrency automatically. * metal : code style changes --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
143 KiB
143 KiB