root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

simple : update error message for KV cache check (#4324)

Browse Source 
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 <daniel.bevenius@gmail.com>
This commit is contained in:
Daniel Bevenius 2023-12-04 17:04:21 +01:00 committed by GitHub
parent d208995c6d
commit 23b5e12eb5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/simple/simple.cpp
View File

@ -75,7 +75,7 @@ int main(int argc, char ** argv) {
// make sure the KV cache is big enough to hold all the prompt and generated tokens // make sure the KV cache is big enough to hold all the prompt and generated tokens
if (n_kv_req > n_ctx) { if (n_kv_req > n_ctx) {
LOG_TEE("%s: error: n_kv_req > n_ctx, the required KV cache size is not big enough\n", __func__); LOG_TEE("%s: error: n_kv_req > n_ctx, the required KV cache size is not big enough\n", __func__);
LOG_TEE("%s: either reduce n_parallel or increase n_ctx\n", __func__); LOG_TEE("%s: either reduce n_len or increase n_ctx\n", __func__);
return 1; return 1;
} }