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

llama : use the same threshold for OpenBLAS and ggml thread limiting (#577)

Browse source
This commit is contained in:
Maël Kerbiriou 2023-03-29 18:10:07 +02:00 committed by GitHub
parent a6956b25a1
commit 41318d708e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -856,7 +856,7 @@ 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 > 255 && ggml_cpu_has_blas() ? 1 : n_threads;
gf.n_threads = N >= 32 && ggml_cpu_has_blas() ? 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));