thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama_fit_params: return enum for fail vs. error (#18374)

Browse source
This commit is contained in:
Johannes Gäßler 2025-12-27 09:59:19 +01:00 • committed by GitHub
parent 9045c9afe5
commit a52dc60ba3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 28 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

8
include/llama.h
View file

@ -467,10 +467,16 @@ extern "C" {
// Frees all allocated memory
LLAMA_API void llama_free(struct llama_context * ctx);
enum llama_params_fit_status {
LLAMA_PARAMS_FIT_STATUS_SUCCESS = 0, // found allocations that are projected to fit
LLAMA_PARAMS_FIT_STATUS_FAILURE = 1, // could not find allocations that are projected to fit
LLAMA_PARAMS_FIT_STATUS_ERROR = 2, // a hard error occured, e.g. because no model could be found at the specified path
};
// fits mparams and cparams to free device memory (assumes system memory is unlimited)
// returns true if the parameters could be successfully modified to fit device memory
// this function is NOT thread safe because it modifies the global llama logger state
LLAMA_API bool llama_params_fit(
LLAMA_API enum llama_params_fit_status llama_params_fit(
const char * path_model,
struct llama_model_params * mparams,
struct llama_context_params * cparams,