vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing

Browse source
This commit is contained in:
0cc4m 2023-04-10 09:49:40 +02:00
parent 69b85f5b61
commit c3db99ea32
3 changed files with 134 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_adapter.cpp
View file

@ -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
}
}
}