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

llama : add getters for n_threads/n_threads_batch

Browse source 
This commit adds two new functions to the llama API. The functions
can be used to get the number of threads used for generating a single
token and the number of threads used for prompt and batch processing
(multiple tokens).

The motivation for this is that we want to be able to get the number of
threads that the a context is using. The main use case is for a
testing/verification that the number of threads is set correctly.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
This commit is contained in:
Daniel Bevenius 2024-05-22 15:11:01 +02:00
parent 1e374365d1
commit 43f1d316f5
Failed to extract signature
2 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama.cpp
View file

@ -17183,6 +17183,14 @@ void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_
ctx->cparams.n_threads_batch = n_threads_batch;
}
uint32_t llama_get_n_threads(struct llama_context * ctx) {
return ctx->cparams.n_threads;
}
uint32_t llama_get_n_threads_batch(struct llama_context * ctx) {
return ctx->cparams.n_threads_batch;
}
void llama_set_abort_callback(struct llama_context * ctx, bool (*abort_callback)(void * data), void * abort_callback_data) {
ctx->abort_callback = abort_callback;
ctx->abort_callback_data = abort_callback_data;

6
llama.h
View file

@ -759,6 +759,12 @@ extern "C" {
// n_threads_batch is the number of threads used for prompt and batch processing (multiple tokens)
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch);
// Get the number of threads used for generation of a single token.
LLAMA_API uint32_t llama_get_n_threads(struct llama_context * ctx);
// Get the number of threads used for prompt and batch processing (multiple token).
LLAMA_API uint32_t llama_get_n_threads_batch(struct llama_context * ctx);
// Set whether to use causal attention or not
// If set to true, the model will only attend to the past tokens
LLAMA_API void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn);