CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix params struct slignment (#1936)

Browse Source 
* Workaround struct misalignment during value-copy

Signed-off-by: mudler <mudler@localai.io>

* Move booleans at the bottom of the structure

Signed-off-by: mudler <mudler@localai.io>

* Add comment

Signed-off-by: mudler <mudler@localai.io>

---------

Signed-off-by: mudler <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2023-06-20 03:24:39 +02:00
committed by GitHub
parent 20568fe60f
commit aacdbd4056
2 changed files with 11 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llama.cpp
View File

@@ -925,21 +925,21 @@ static bool kv_cache_init(
struct llama_context_params llama_context_default_params() {
struct llama_context_params result = {
/*.seed =*/ -1,
/*.n_ctx =*/ 512,
/*.n_batch =*/ 512,
/*.gpu_layers =*/ 0,
/*.main_gpu =*/ 0,
/*.tensor_split =*/ {0},
/*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr,
/*.low_vram =*/ false,
/*.seed =*/ -1,
/*.f16_kv =*/ true,
/*.logits_all =*/ false,
/*.vocab_only =*/ false,
/*.use_mmap =*/ true,
/*.use_mlock =*/ false,
/*.embedding =*/ false,
/*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr,
};
return result;

15
llama.h
View File

@@ -72,27 +72,26 @@ extern "C" {
typedef void (*llama_progress_callback)(float progress, void *ctx);
struct llama_context_params {
int seed; // RNG seed, -1 for random
int n_ctx; // text context
int n_batch; // prompt processing batch size
int n_gpu_layers; // number of layers to store in VRAM
int main_gpu; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES]; // how to split layers across multiple GPUs
bool low_vram; // if true, reduce VRAM usage at the cost of performance
int seed; // RNG seed, -1 for random
// called with a progress value between 0 and 1, pass NULL to disable
llama_progress_callback progress_callback;
// context pointer passed to the progress callback
void * progress_callback_user_data;
// Keep the booleans together to avoid misalignment during copy-by-value.
bool low_vram; // if true, reduce VRAM usage at the cost of performance
bool f16_kv; // use fp16 for KV cache
bool logits_all; // the llama_eval() call computes all logits, not just the last one
bool vocab_only; // only load the vocabulary, no weights
bool use_mmap; // use mmap if possible
bool use_mlock; // force system to keep model in RAM
bool embedding; // embedding mode only
// called with a progress value between 0 and 1, pass NULL to disable
llama_progress_callback progress_callback;
// context pointer passed to the progress callback
void * progress_callback_user_data;
};
// model file types
enum llama_ftype {
LLAMA_FTYPE_ALL_F32 = 0,