chore: clean useless beam search param (#7985)

Signed-off-by: thxCode <redacted>

diff --git a/common/common.h b/common/common.h
index 58ed72f433bdf569e4e9868a776e95f9d3958d58..9a1dc4a2fe4c1b49993e02cd8e2c67d112525c48 100644 (file)
--- 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)