mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-30 09:00:49 +02:00
Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing
This commit is contained in:
@@ -251,10 +251,12 @@ generation_outputs llama_generate(const generation_inputs inputs, generation_out
|
||||
last_n_tokens.push_back(embd_inp[input_consumed]);
|
||||
current_context_tokens.push_back(embd_inp[input_consumed]);
|
||||
++input_consumed;
|
||||
#ifndef GGML_USE_CLBLAST
|
||||
if ((int)embd.size() >= params.n_batch)
|
||||
{
|
||||
break;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user