]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bfb4c74)
common : add --no-warmup option for main/llama-cli (#8712)
authorDaniel Bevenius <redacted>
Sat, 27 Jul 2024 10:45:02 +0000 (12:45 +0200)
committerGitHub <redacted>
Sat, 27 Jul 2024 10:45:02 +0000 (13:45 +0300)
commit9d03d085dd6cb275c078690bb64073b9b043e95f
treefb23bc7f396e90e9643ba6f4d921fe75771172cftree
parentbfb4c74981f0a40d757b450b596a9fe4ca983d26commit | diff
common : add --no-warmup option for main/llama-cli (#8712)

This commit adds a --no-warmup option for llama-cli.

The motivation for this is that it can be convenient to skip the
warmup llama_decode call when debugging.

Signed-off-by: Daniel Bevenius <redacted>
common/common.cpp diff | blob | history
Packaging of ggml-org/llama.cpp