diff options
| author | Frank Mai <thxcode0824@gmail.com> | 2024-06-18 15:11:40 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-18 10:11:40 +0300 |
| commit | b96f9afb0d58b003ac8d1d0c94cd99393a3bc437 (patch) | |
| tree | 19ccda3cdba51b3b58183403ba277ba671fcd33b | |
| parent | 1193778105c9a81bd38f72c61aaafbaf85dc9c04 (diff) | |
chore: clean useless beam search param (#7985)
Signed-off-by: thxCode <thxcode0824@gmail.com>
| -rw-r--r-- | common/common.h | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/common/common.h b/common/common.h index 58ed72f4..9a1dc4a2 100644 --- a/common/common.h +++ b/common/common.h @@ -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 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_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_w = 512; // group-attention width int32_t n_print = -1; // print token count every n tokens (-1 = disabled) |