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

Add NVIDIA cuBLAS support (#1044)

Browse source
This commit is contained in:
slaren 2023-04-19 11:22:45 +02:00 • committed by GitHub
parent 6667401238
commit 8944a13296
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 221 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1069,7 +1069,7 @@ static bool llama_eval_internal(
// for big prompts, if BLAS is enabled, it is better to use only one thread
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
ggml_cgraph gf = {};
gf.n_threads = N >= 32 && ggml_cpu_has_blas() ? 1 : n_threads;
gf.n_threads = N >= 32 && ggml_cpu_has_blas() && !ggml_cpu_has_cublas() ? 1 : n_threads;
struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
memcpy(embd->data, tokens, N*ggml_element_size(embd));