happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Corrected spelling of 'beacause' to 'because'. 

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
CyanFalse 2026-03-08 17:05:03 +08:00 committed by GitHub
parent 907200d737
commit 27b023ce9a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-common.cpp
View File

@ -415,7 +415,7 @@ void server_tokens::keep_first(size_t n) {
// note that the case where we keep a full image at the end is allowed:
// tokens[n - 1] == LLAMA_TOKEN_NULL && tokens[n] != LLAMA_TOKEN_NULL
if (has_precomputed) { //if it is precomputed, we only need to check if the previous token is precomputed.
find_precomputed(n - 1); // must be find_precomputed but not find_chunk.beacause it knows more than mtmd chunk
find_precomputed(n - 1); // must be find_precomputed but not find_chunk.because it knows more than mtmd chunk
}
else if (tokens[n - 1] == LLAMA_TOKEN_NULL && tokens[n] == LLAMA_TOKEN_NULL) {
find_chunk(n - 1); // will throw an error if the token is not begin-of-chunk