Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 06:10:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

Don't interefe with BLAS for large prompts by running only 1 thread

Browse Source
This commit is contained in:
Georgi Gerganov 2023-03-25 17:03:10 +02:00
parent ab77d76312
commit 4640eff23d
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llama.cpp
View File

@ -852,8 +852,11 @@ static bool llama_eval_internal(
}; };
struct ggml_context * ctx0 = ggml_init(params); struct ggml_context * ctx0 = ggml_init(params);
// 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 = {}; ggml_cgraph gf = {};
gf.n_threads = n_threads; gf.n_threads = N > 255 && ggml_cpu_has_blas() ? 1 : n_threads;
struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N); struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
memcpy(embd->data, tokens, N*ggml_element_size(embd)); memcpy(embd->data, tokens, N*ggml_element_size(embd));