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

squash! llama : add getters for n_threads/n_threads_batch

Browse source 
Rename the getters to llama_n_threads and llama_n_threads_batch.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
This commit is contained in:
Daniel Bevenius 2024-05-22 16:17:00 +02:00
parent 43f1d316f5
commit 43bcb50f13
Failed to extract signature
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -17183,11 +17183,11 @@ void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_
ctx->cparams.n_threads_batch = n_threads_batch; ctx->cparams.n_threads_batch = n_threads_batch;
} }
uint32_t llama_get_n_threads(struct llama_context * ctx) { uint32_t llama_n_threads(struct llama_context * ctx) {
return ctx->cparams.n_threads; return ctx->cparams.n_threads;
} }
uint32_t llama_get_n_threads_batch(struct llama_context * ctx) { uint32_t llama_n_threads_batch(struct llama_context * ctx) {
return ctx->cparams.n_threads_batch; return ctx->cparams.n_threads_batch;
} }

4
llama.h
View file

@ -760,10 +760,10 @@ extern "C" {
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch); 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. // Get the number of threads used for generation of a single token.
LLAMA_API uint32_t llama_get_n_threads(struct llama_context * ctx); LLAMA_API uint32_t llama_n_threads(struct llama_context * ctx);
// Get the number of threads used for prompt and batch processing (multiple token). // 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); LLAMA_API uint32_t llama_n_threads_batch(struct llama_context * ctx);
// Set whether to use causal attention or not // Set whether to use causal attention or not
// If set to true, the model will only attend to the past tokens // If set to true, the model will only attend to the past tokens