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

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

Browse source 
* llama: automatically fit args to free memory

llama-fit-params tool

* fix CI

* hints for bug reports, ensure no reallocation

* fix segfault with Vulkan

* add llama-fit-params to CI

* fix CI

* fix CI

* fix CI

* minor adjustments

* fix assignment of 1 dense layer

* fix logger not being reset on model load failure

* remove --n-gpu-layer hint on model load failure

* fix llama-fit-params verbosity

* fix edge case

* fix typo [no ci]
This commit is contained in:
Johannes Gäßler 2025-12-15 09:24:59 +01:00 • committed by GitHub
parent 4aced7a631
commit b1f3a6e5db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 1075 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-model-loader.cpp
View file

@ -473,6 +473,7 @@ llama_model_loader::llama_model_loader(
std::vector<std::string> & splits,
bool use_mmap,
bool check_tensors,
bool no_alloc,
const llama_model_kv_override * param_overrides_p,
const llama_model_tensor_buft_override * param_tensor_buft_overrides_p) {
int trace = 0;
@ -716,6 +717,7 @@ llama_model_loader::llama_model_loader(
this->use_mmap = use_mmap;
this->check_tensors = check_tensors;
this->no_alloc = no_alloc;
}
std::string llama_model_loader::get_arch_name() const {