M2 Pro 32GB Cannot Use Metal #3580

uetuluk · 2023-10-11T09:46:46Z

uetuluk
Oct 11, 2023

I am trying to run llama.cpp with the following model https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGUF/tree/main, however, I cannot seem to make the GPU support work.

I build llama.cpp with make as instructed, however, when I try to run any model with --ngl 1 flag, I get the following error.

./main -m ./codellama-13b-instruct.Q6_K.gguf --n_gpu_layers 1
Log start
main: build = 1364 (9f6ede1)
main: built with clang version 14.0.6 for arm64-apple-darwin20.0.0
main: seed  = 1697017297
llama_model_loader: loaded meta data with 20 key-value pairs and 363 tensors from ./codellama-13b-instruct.Q6_K.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q6_K     [  5120, 32016,     1,     1 ]
llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor    7:         blk.0.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor    8:              blk.0.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   16:         blk.1.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   17:              blk.1.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   24:             blk.10.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   25:        blk.10.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   26:             blk.10.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   27:             blk.10.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   33:             blk.11.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   34:        blk.11.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   35:             blk.11.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   36:             blk.11.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   42:             blk.12.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   43:        blk.12.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   44:             blk.12.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   45:             blk.12.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   51:             blk.13.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   52:        blk.13.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   53:             blk.13.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   54:             blk.13.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   60:             blk.14.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   61:        blk.14.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   62:             blk.14.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   63:             blk.14.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   64:             blk.15.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   65:             blk.15.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   66:           blk.2.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   67:            blk.2.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   68:            blk.2.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   69:              blk.2.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   70:            blk.2.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   71:              blk.2.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   72:         blk.2.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   73:              blk.2.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   74:              blk.2.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   75:           blk.3.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   76:            blk.3.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   77:            blk.3.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   78:              blk.3.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   79:            blk.3.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   80:              blk.3.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   81:         blk.3.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   82:              blk.3.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   83:              blk.3.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   84:           blk.4.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   85:            blk.4.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   86:            blk.4.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   87:              blk.4.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   88:            blk.4.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   89:              blk.4.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   90:         blk.4.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   91:              blk.4.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   92:              blk.4.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   93:           blk.5.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   94:            blk.5.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor   95:            blk.5.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   96:              blk.5.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor   97:            blk.5.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor   98:              blk.5.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor   99:         blk.5.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  100:              blk.5.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  101:              blk.5.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  102:           blk.6.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  103:            blk.6.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  104:            blk.6.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  105:              blk.6.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  106:            blk.6.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  107:              blk.6.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  108:         blk.6.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  109:              blk.6.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  110:              blk.6.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  111:           blk.7.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  112:            blk.7.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  113:            blk.7.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  114:              blk.7.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  115:            blk.7.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  116:              blk.7.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  117:         blk.7.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  118:              blk.7.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  119:              blk.7.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  120:           blk.8.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  121:            blk.8.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  122:            blk.8.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  123:              blk.8.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  124:            blk.8.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  125:              blk.8.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  126:         blk.8.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  127:              blk.8.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  128:              blk.8.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  129:           blk.9.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  130:            blk.9.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  131:            blk.9.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  132:              blk.9.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  133:            blk.9.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  134:              blk.9.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  135:         blk.9.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  136:              blk.9.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  137:              blk.9.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  138:          blk.15.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  139:           blk.15.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  143:        blk.15.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  145:          blk.16.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.16.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  147:           blk.16.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  149:           blk.16.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  150:             blk.16.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  151:        blk.16.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  152:             blk.16.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  154:          blk.17.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.17.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  156:           blk.17.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  158:           blk.17.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  159:             blk.17.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  160:        blk.17.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  161:             blk.17.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  163:          blk.18.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.18.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  165:           blk.18.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  167:           blk.18.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  168:             blk.18.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  169:        blk.18.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  170:             blk.18.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  172:          blk.19.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.19.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  174:           blk.19.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  176:           blk.19.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  177:             blk.19.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  178:        blk.19.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  179:             blk.19.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  181:          blk.20.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.20.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  183:           blk.20.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  185:           blk.20.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  186:             blk.20.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  187:        blk.20.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  188:             blk.20.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  190:          blk.21.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.21.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  192:           blk.21.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  194:           blk.21.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  195:             blk.21.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  196:        blk.21.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  197:             blk.21.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  199:          blk.22.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.22.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  201:           blk.22.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  203:           blk.22.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  204:             blk.22.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  205:        blk.22.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  206:             blk.22.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  208:          blk.23.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.23.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  210:           blk.23.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  212:           blk.23.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  213:             blk.23.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  214:        blk.23.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  215:             blk.23.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  217:          blk.24.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.24.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  219:           blk.24.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  221:           blk.24.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  222:             blk.24.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  223:        blk.24.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  224:             blk.24.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  226:          blk.25.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.25.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  228:           blk.25.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  230:           blk.25.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  231:             blk.25.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  232:        blk.25.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  233:             blk.25.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  235:          blk.26.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.26.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  237:           blk.26.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  239:           blk.26.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  240:             blk.26.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  241:        blk.26.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  242:             blk.26.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  244:          blk.27.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.27.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  246:           blk.27.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  248:           blk.27.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  249:             blk.27.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  250:        blk.27.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  251:             blk.27.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  253:          blk.28.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.28.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  255:           blk.28.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  257:           blk.28.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  258:             blk.28.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  259:        blk.28.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  260:             blk.28.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  262:          blk.29.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.29.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  264:           blk.29.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  266:           blk.29.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  267:             blk.29.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  268:        blk.29.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  269:             blk.29.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  271:           blk.30.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  272:             blk.30.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  274:        blk.30.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  276:             blk.30.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  277:                    output.weight q6_K     [  5120, 32016,     1,     1 ]
llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  279:           blk.30.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  280:           blk.30.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  286:             blk.31.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  287:        blk.31.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  289:             blk.31.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  290:          blk.32.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  291:           blk.32.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  292:           blk.32.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  293:             blk.32.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  294:           blk.32.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  295:             blk.32.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  296:        blk.32.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  297:             blk.32.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  298:             blk.32.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  299:          blk.33.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  300:           blk.33.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  301:           blk.33.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  302:             blk.33.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  303:           blk.33.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  304:             blk.33.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  305:        blk.33.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  306:             blk.33.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  307:             blk.33.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  308:          blk.34.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  309:           blk.34.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  310:           blk.34.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  311:             blk.34.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  312:           blk.34.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  313:             blk.34.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  314:        blk.34.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  315:             blk.34.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  316:             blk.34.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  317:          blk.35.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  318:           blk.35.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  319:           blk.35.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  320:             blk.35.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  321:           blk.35.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  322:             blk.35.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  323:        blk.35.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  324:             blk.35.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  325:             blk.35.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  326:          blk.36.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  327:           blk.36.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  328:           blk.36.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  329:             blk.36.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  330:           blk.36.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  331:             blk.36.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  332:        blk.36.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  333:             blk.36.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  334:             blk.36.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  335:          blk.37.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  336:           blk.37.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  337:           blk.37.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  338:             blk.37.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  339:           blk.37.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  340:             blk.37.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  341:        blk.37.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  342:             blk.37.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  343:             blk.37.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  344:          blk.38.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  345:           blk.38.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  346:           blk.38.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  347:             blk.38.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  348:           blk.38.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  349:             blk.38.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  350:        blk.38.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  351:             blk.38.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  352:             blk.38.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  353:          blk.39.attn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  354:           blk.39.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
llama_model_loader: - tensor  355:           blk.39.ffn_gate.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  356:             blk.39.ffn_up.weight q6_K     [  5120, 13824,     1,     1 ]
llama_model_loader: - tensor  357:           blk.39.ffn_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - tensor  358:             blk.39.attn_k.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  359:        blk.39.attn_output.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  360:             blk.39.attn_q.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  361:             blk.39.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]
llama_model_loader: - tensor  362:               output_norm.weight f32      [  5120,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str     
llama_model_loader: - kv   1:                               general.name str     
llama_model_loader: - kv   2:                       llama.context_length u32     
llama_model_loader: - kv   3:                     llama.embedding_length u32     
llama_model_loader: - kv   4:                          llama.block_count u32     
llama_model_loader: - kv   5:                  llama.feed_forward_length u32     
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     
llama_model_loader: - kv   7:                 llama.attention.head_count u32     
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     
llama_model_loader: - kv  10:                       llama.rope.freq_base f32     
llama_model_loader: - kv  11:                          general.file_type u32     
llama_model_loader: - kv  12:                       tokenizer.ggml.model str     
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr     
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr     
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr     
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32     
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32     
llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32     
llama_model_loader: - kv  19:               general.quantization_version u32     
llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q6_K:  282 tensors
llm_load_print_meta: format           = GGUF V2 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32016
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 16384
llm_load_print_meta: n_embd           = 5120
llm_load_print_meta: n_head           = 40
llm_load_print_meta: n_head_kv        = 40
llm_load_print_meta: n_layer          = 40
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff             = 13824
llm_load_print_meta: freq_base_train  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: model type       = 13B
llm_load_print_meta: model ftype      = mostly Q6_K
llm_load_print_meta: model params     = 13.02 B
llm_load_print_meta: model size       = 9.95 GiB (6.56 BPW) 
llm_load_print_meta: general.name   = codellama_codellama-13b-instruct-hf
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.12 MB
llm_load_tensors: mem required  = 10183.96 MB
....................................................................................................
llama_new_context_with_model: n_ctx      = 512
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size  =  400.00 MB
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2 Pro
ggml_metal_init: picking default device: (null)
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: loading './llama.cpp/ggml-metal.metal'
ggml_metal_init: loaded kernel_add                                    0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_add_row                                0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul                                    0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_row                                0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_scale                                  0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_silu                                   0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_relu                                   0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_gelu                                   0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_soft_max                               0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_soft_max_4                             0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_diag_mask_inf                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_diag_mask_inf_8                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_f32                           0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_f16                           0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q4_0                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q4_1                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q8_0                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q2_K                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q3_K                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q4_K                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q5_K                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_get_rows_q6_K                          0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_rms_norm                               0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_norm                                   0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_f32_f32                         0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_f16_f32                         0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_f16_f32_1row                    0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_f16_f32_l4                      0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q4_0_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q4_1_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q8_0_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q2_K_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q3_K_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q4_K_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q5_K_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_mul_mv_q6_K_f32                        0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_rope_f32                               0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_rope_f16                               0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_alibi_f32                              0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_cpy_f32_f16                            0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_cpy_f32_f32                            0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_cpy_f16_f16                            0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_concat                                 0x0 | th_max =    0 | th_width =    0
ggml_metal_init: loaded kernel_sqr                                    0x0 | th_max =    0 | th_width =    0
ggml_metal_init: GPU name:   (null)
ggml_metal_init: hasUnifiedMemory              = false
ggml_metal_init: recommendedMaxWorkingSetSize  =     0.00 MB
ggml_metal_init: maxTransferRate               = built-in GPU
llama_new_context_with_model: compute buffer total size = 81.13 MB
llama_new_context_with_model: max tensor size =   128.24 MB
ggml_metal_add_buffer: error: failed to allocate 'data            ' buffer, size =     0.00 MB
llama_new_context_with_model: failed to add buffer
ggml_metal_free: deallocating
llama_init_from_gpt_params: error: failed to create context with model './codellama-13b-instruct.Q6_K.gguf'
main: error: unable to load model

Answered by uetuluk

Oct 12, 2023

My case was caused by something in the terminal configuration. Here is how I built llama.cpp to avoid this issue.

Creating a terminal without any configuration

env -i zsh -f

Running make -j inside this terminal

View full answer

uetuluk · 2023-10-11T09:48:06Z

uetuluk
Oct 11, 2023
Author

I saw that there is a similar issue #3423, however, there is no conclusion.

2 replies

KerfuffleV2 Oct 11, 2023
Collaborator

Think that's a different issue. The first person had a problem compiling with shared libraries turned on. The other one was trying to get Metal working on an Intel Mac (which may never have worked).

uetuluk Oct 12, 2023
Author

Ah, thank you for the clarification.

The following sections seem interesting to me.

ggml_metal_init: found device: Apple M2 Pro
ggml_metal_init: picking default device: (null)
...
ggml_metal_init: GPU name:   (null)
ggml_metal_init: hasUnifiedMemory              = false
ggml_metal_init: recommendedMaxWorkingSetSize  =     0.00 MB
ggml_metal_init: maxTransferRate               = built-in GPU

ianscrivener · 2023-10-12T03:26:03Z

ianscrivener
Oct 12, 2023

@uetuluk,
On my Mac I have before build both with make and cmake,
though I usually build with make clean && LLAMA_METAL=1 make -j
(note: Metal is now default on for MacOS)

What was your exact build process? Do both make and cmake fail for you?

10 replies

ianscrivener Oct 12, 2023

pls confirm you are running MacOS with M1 or M2:

% uname -a
Darwin Ians-MacBook-Pro.local 23.0.0 Darwin Kernel Version 23.0.0: Fri Sep 15 14:42:57 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T8112 arm64

uetuluk Oct 12, 2023
Author

Those are all fine.

/Library/Developer/CommandLineTools
Same as yours.
root:xnu-10002.1.13~1/RELEASE_ARM64_T6020 arm64

I have anaconda installed, so that might be the problem.

ianscrivener Oct 12, 2023

Anaconda shouldn't make any difference.. as there is no python involved in the C/C++ build
BTW: I've succcessfully used cmake & make inside and outside conda environments...

uetuluk Oct 12, 2023
Author

It was something in the environment.

I created a terminal instance with the command env -i zsh -f to not load anything.

It works after running make inside this environment.

uetuluk Oct 12, 2023
Author

@ianscrivener Thank you for the help!

I will try to isolate whatever is causing the problem.

ianscrivener · 2023-10-12T04:21:31Z

ianscrivener
Oct 12, 2023

out of the box thought:
can you make/install llama-cpp-python in a conda env?
CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir --upgrade

2 replies

uetuluk Oct 12, 2023
Author

Yes, that does work.

ianscrivener Oct 12, 2023

So perhaps try testing llama-cpp-python.

pip install "llama-cpp-python[server]"
python3 -m llama_cpp.server --model models/7B/llama-model.gguf

then you can test llama.cpp with the the OpenAI~Ish API at (http://localhost:8000/docs)

ianscrivener · 2023-10-12T04:25:09Z

ianscrivener
Oct 12, 2023

Also,
does Metal work OK in python?

pip3 install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cpu

python-test-MPS.py

import torch
print(f"PyTorch version: {torch.__version__}")

# Check PyTorch has access to MPS (Metal Performance Shader, Apple's GPU architecture)
print(f"Is MPS (Metal Performance Shader) built? {torch.backends.mps.is_built()}")
print(f"Is MPS available? {torch.backends.mps.is_available()}")

# Set the device      
device = "mps" if torch.backends.mps.is_available() else "cpu"
print(f"Using device: {device}")

1 reply

uetuluk Oct 12, 2023
Author

Is MPS available? True
Using device: mps

uetuluk · 2023-10-12T04:28:18Z

uetuluk
Oct 12, 2023
Author

My case was caused by something in the terminal configuration. Here is how I built llama.cpp to avoid this issue.

Creating a terminal without any configuration

env -i zsh -f

Running make -j inside this terminal

2 replies

ianscrivener Oct 12, 2023

well done!

remixer-dec Dec 17, 2023

Thanks a lot! This worked for me as well.

M2 Pro 32GB Cannot Use Metal #3580

Uh oh!

Uh oh!

Replies: 5 comments · 17 replies

Uh oh!

uetuluk Oct 11, 2023 Author

Uh oh!

KerfuffleV2 Oct 11, 2023 Collaborator

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

Uh oh!

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

Uh oh!

Uh oh!

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

uetuluk Oct 12, 2023 Author

Uh oh!

Uh oh!

Replies: 5 comments 17 replies

uetuluk
Oct 11, 2023
Author

KerfuffleV2 Oct 11, 2023
Collaborator

uetuluk Oct 12, 2023
Author

uetuluk Oct 12, 2023
Author

uetuluk Oct 12, 2023
Author

uetuluk Oct 12, 2023
Author

uetuluk Oct 12, 2023
Author

uetuluk Oct 12, 2023
Author

uetuluk
Oct 12, 2023
Author