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-quant.cpp
View file

@ -596,7 +596,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
}
std::vector<std::string> splits = {};
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, kv_overrides, nullptr);
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());