vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #9 from WangHaoranRobin/robin_fork_master

Browse source 
examples/common.h: put all bool variables in gpt_params together
This commit is contained in:
WangHaoranRobin 2023-07-02 08:02:14 +08:00 • committed by GitHub
commit cc3c86f6ea
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/common.h
View file

@ -31,7 +31,6 @@ struct gpt_params {
int32_t n_gpu_layers = 0; // number of layers to store in VRAM int32_t n_gpu_layers = 0; // number of layers to store in VRAM
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
bool low_vram = 0; // if true, reduce VRAM usage at the cost of performance
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens. int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
// sampling parameters // sampling parameters
@ -60,6 +59,7 @@ struct gpt_params {
std::string lora_adapter = ""; // lora adapter path std::string lora_adapter = ""; // lora adapter path
std::string lora_base = ""; // base model path for the lora adapter std::string lora_base = ""; // base model path for the lora adapter
bool low_vram = false; // if true, reduce VRAM usage at the cost of performance
bool memory_f16 = true; // use f16 instead of f32 for memory kv bool memory_f16 = true; // use f16 instead of f32 for memory kv
bool random_prompt = false; // do not randomize prompt if none provided bool random_prompt = false; // do not randomize prompt if none provided
bool use_color = false; // use color to distinguish generations and inputs bool use_color = false; // use color to distinguish generations and inputs