tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

perplexity : provide a helpful hint for has_cpl case in split_equal error. (#15304)

Browse Source 
When attempting to do llama-perplexity on certain tasks which have coupled sequences there is a cryptic error that does not tell you what to do, which is to set the -kvu flag. This adds a hint about that fact.
This commit is contained in:
kallewoof
2025-08-14 20:03:30 +09:00
committed by GitHub
parent 4ebd0c125b
commit 810b9fc8b9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-batch.cpp
View File

@@ -477,7 +477,7 @@ llama_ubatch llama_batch_allocr::split_simple(uint32_t n_ubatch) {
llama_ubatch llama_batch_allocr::split_equal(uint32_t n_ubatch, bool sequential) { llama_ubatch llama_batch_allocr::split_equal(uint32_t n_ubatch, bool sequential) {
if (sequential && has_cpl) { if (sequential && has_cpl) {
LLAMA_LOG_ERROR("%s: sequential split is not supported when there are coupled sequences in the input batch\n", __func__); LLAMA_LOG_ERROR("%s: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag)\n", __func__);
return {}; return {};
} }