]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: d208995)
simple : update error message for KV cache check (#4324)
authorDaniel Bevenius <redacted>
Mon, 4 Dec 2023 16:04:21 +0000 (17:04 +0100)
committerGitHub <redacted>
Mon, 4 Dec 2023 16:04:21 +0000 (18:04 +0200)
commit23b5e12eb5a76489b4c3ee22213a081da68b1809
tree5b452f782b88e1f8536c2c1774fe0108ee9898fdtree
parentd208995c6da66f252d4054c1c5a90eb8ccb7a2f7commit | diff
simple : update error message for KV cache check (#4324)

This commit updates the error message that is printed when the
KV cache is not big enough to hold all the prompt and generated
tokens. Specifically it removes the reference to n_parallel and
replaces it with n_len.

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