vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cont

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-23 17:32:11 +03:00
parent 56657e52e5
commit d228bf8552
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -15092,7 +15092,7 @@ struct llama_context * llama_new_context_with_model(
// ref: https://github.com/ggerganov/llama.cpp/pull/5021 // ref: https://github.com/ggerganov/llama.cpp/pull/5021
if (cparams.n_batch < GGML_KQ_MASK_PAD) { if (cparams.n_batch < GGML_KQ_MASK_PAD) {
LLAMA_LOG_WARN("%s: n_batch is less than GGML_KQ_MASK_PAD - increasing to %d\n", __func__, GGML_KQ_MASK_PAD); LLAMA_LOG_WARN("%s: n_batch is less than GGML_KQ_MASK_PAD - increasing to %d\n", __func__, GGML_KQ_MASK_PAD);
cparams.n_batch = std::max((uint32_t) GGML_KQ_MASK_PAD, params.n_batch); cparams.n_batch = GGML_KQ_MASK_PAD;
} }
cparams.n_ubatch = std::min(cparams.n_batch, params.n_ubatch == 0 ? params.n_batch : params.n_ubatch); cparams.n_ubatch = std::min(cparams.n_batch, params.n_ubatch == 0 ? params.n_batch : params.n_ubatch);