Start using ggml-alloc in SAM example

[YavorGIvanov]

• Remove scratch buffers from image encoder
• This change makes the whole inference a bit slower. I will additionally investigate why this happens and speed it up again.
• There are two additional ggml_allocr_alloc(..) calls, which should NOT be needed after the ggml_conv_transpose_2d_p0(..) operation. This will also be fixed additionally.

[ggerganov]

M2 Ultra speed:

 $ ▶ make -j sam && time ./bin/sam -t 8 -i img.jpg
[ 28%] Built target common
[ 71%] Built target ggml
[100%] Built target sam
main: seed = 1693224265
main: loaded image 'img.jpg' (680 x 453)
sam_image_preprocess: scale = 0.664062
main: preprocessed image (1024 x 1024)
sam_model_load: loading model from 'models/sam-vit-b/ggml-model-f16.bin' - please wait ...
sam_model_load: n_enc_state      = 768
sam_model_load: n_enc_layer      = 12
sam_model_load: n_enc_head       = 12
sam_model_load: n_enc_out_chans  = 256
sam_model_load: n_pt_embd        = 4
sam_model_load: ftype            = 1
sam_model_load: qntvr            = 0
operator(): ggml ctx size = 202.32 MB
sam_model_load: ...................................... done
sam_model_load: model size =   185.05 MB / num tensors = 304
embd_img
dims: 64 64 256 1 f32
First & Last 10 elements:
-0.05117 -0.06408 -0.07154 -0.06991 -0.07212 -0.07690 -0.07508 -0.07281 -0.07383 -0.06779 
0.01589 0.01775 0.02250 0.01675 0.01766 0.01661 0.01811 0.02051 0.02103 0.03382 
sum:  12736.272313

Skipping mask 0 with iou 0.705935 below threshold 0.880000
Skipping mask 1 with iou 0.762136 below threshold 0.880000
Mask 2: iou = 0.947081, stability_score = 0.955437, bbox (371, 436), (144, 168)


main:     load time =    51.28 ms
main:    total time =  2047.49 ms

real	0m2.068s
user	0m16.343s
sys	0m0.214s

[ggerganov]

In the future, this should become ggml_disconnect part of ggml