nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 17 Packages Projects Releases Wiki Activity

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
26 changed files with 1075 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.h
+9 -5
View File
@@ -99,6 +99,7 @@ enum llama_example {
LLAMA_EXAMPLE_TTS,
LLAMA_EXAMPLE_DIFFUSION,
LLAMA_EXAMPLE_FINETUNE,
LLAMA_EXAMPLE_FIT_PARAMS,
LLAMA_EXAMPLE_COUNT,
};
@@ -306,8 +307,8 @@ struct lr_opt {
struct ggml_opt_optimizer_params common_opt_lr_pars(void * userdata);
struct common_params {
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 4096; // context size
int32_t n_predict = -1; // max. number of new tokens to predict, -1 == no limit
int32_t n_ctx = 0; // context size, 0 == context the model was trained with
int32_t n_batch = 2048; // logical batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_ubatch = 512; // physical batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
@@ -328,9 +329,12 @@ struct common_params {
// offload params
std::vector<ggml_backend_dev_t> devices; // devices to use for offloading
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs
bool fit_params = true; // whether to fit unset model/context parameters to free device memory
size_t fit_params_target = 1024 * 1024*1024; // margin per device in bytes for fitting parameters to free memory
int32_t fit_params_min_ctx = 4096; // minimum context size to set when trying to reduce memory use
enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs