cturan/llama.cpp @ 1204f9727005974587d6fc1dcd4d4f0ead87c856

Georgi Gerganov 0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)		пре 1 година
..
Sources	0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)	пре 1 година
.gitignore	24ba3d829e examples : add batched.swift + improve CI for swift (#3562)	пре 2 година
Makefile	1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	пре 1 година
Package.swift	1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	пре 1 година
README.md	1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	пре 1 година

This is a swift clone of examples/batched.

$ make $ ./llama-batched-swift MODEL_PATH [PROMPT] [PARALLEL]