root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

chore: clean useless beam search param (#7985)

Browse Source 
Signed-off-by: thxCode <thxcode0824@gmail.com>
This commit is contained in:
Frank Mai 2024-06-18 15:11:40 +08:00 committed by GitHub
parent 1193778105
commit b96f9afb0d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.h
View File

@ -73,7 +73,6 @@ struct gpt_params {
int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default) int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default)
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[128] = {0}; // how split tensors should be distributed across GPUs float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs
int32_t n_beams = 0; // if non-zero then use beam search of given width.
int32_t grp_attn_n = 1; // group-attention factor int32_t grp_attn_n = 1; // group-attention factor
int32_t grp_attn_w = 512; // group-attention width int32_t grp_attn_w = 512; // group-attention width
int32_t n_print = -1; // print token count every n tokens (-1 = disabled) int32_t n_print = -1; // print token count every n tokens (-1 = disabled)