Can't do inference with multiple gpu, got ERROR: Segmentation fault (core dumped)

[userbox020]

It loads fine and do inference fine with just one gpu, but when i add a second gop i get the follow output from console

2023-12-27 22:30:20 INFO:Loading dolphin-2.1-mistral-7b.Q6_K.gguf...
2023-12-27 22:30:20 INFO:llama.cpp weights detected: models/dolphin-2.1-mistral-7b.Q6_K.gguf
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 2 ROCm devices:
  Device 0: AMD Radeon RX 6800, compute capability 10.3
  Device 1: AMD Radeon RX 6800, compute capability 10.3
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from models/dolphin-2.1-mistral-7b.Q6_K.gguf (version GGUF V2)
llama_model_loader: - tensor    0:                token_embd.weight q6_K     [  4096, 32002,     1,     1 ]
llama_model_loader: - tensor    1:              blk.0.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    2:              blk.0.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor    4:         blk.0.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    9:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   10:              blk.1.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   11:              blk.1.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   13:         blk.1.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   19:              blk.2.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   20:              blk.2.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   22:         blk.2.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   24:              blk.2.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   28:              blk.3.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   29:              blk.3.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   31:         blk.3.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   33:              blk.3.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   37:              blk.4.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   38:              blk.4.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   40:         blk.4.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   42:              blk.4.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   46:              blk.5.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   47:              blk.5.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   49:         blk.5.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   51:              blk.5.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   55:              blk.6.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   56:              blk.6.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   58:         blk.6.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   60:              blk.6.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   64:              blk.7.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   65:              blk.7.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   67:         blk.7.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   69:              blk.7.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   73:              blk.8.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   74:              blk.8.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   76:         blk.8.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   78:              blk.8.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   82:              blk.9.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   83:              blk.9.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   85:         blk.9.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   87:              blk.9.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   91:             blk.10.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   92:             blk.10.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor   94:        blk.10.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   96:             blk.10.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  100:             blk.11.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  101:             blk.11.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  103:        blk.11.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  105:             blk.11.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  109:             blk.12.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  110:             blk.12.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  112:        blk.12.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  114:             blk.12.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  118:             blk.13.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  119:             blk.13.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  121:        blk.13.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  123:             blk.13.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  127:             blk.14.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  128:             blk.14.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  130:        blk.14.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  132:             blk.14.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  136:             blk.15.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  137:             blk.15.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  139:        blk.15.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  145:             blk.16.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  146:             blk.16.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  148:        blk.16.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  150:             blk.16.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  154:             blk.17.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  155:             blk.17.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  157:        blk.17.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  159:             blk.17.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  163:             blk.18.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  164:             blk.18.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  166:        blk.18.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  168:             blk.18.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  172:             blk.19.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  173:             blk.19.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  175:        blk.19.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  177:             blk.19.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  181:             blk.20.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  182:             blk.20.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  184:        blk.20.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  186:             blk.20.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  190:             blk.21.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  191:             blk.21.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  193:        blk.21.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  195:             blk.21.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  199:             blk.22.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  200:             blk.22.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  202:        blk.22.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  204:             blk.22.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  208:             blk.23.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  209:             blk.23.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  211:        blk.23.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  213:             blk.23.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  217:             blk.24.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  218:             blk.24.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  220:        blk.24.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  222:             blk.24.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  226:             blk.25.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:             blk.25.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  229:        blk.25.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  231:             blk.25.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  235:             blk.26.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:             blk.26.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  238:        blk.26.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  240:             blk.26.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  244:             blk.27.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:             blk.27.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  247:        blk.27.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  249:             blk.27.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  253:             blk.28.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:             blk.28.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  256:        blk.28.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  258:             blk.28.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  262:             blk.29.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:             blk.29.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  265:        blk.29.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  267:             blk.29.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  271:             blk.30.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:             blk.30.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  274:        blk.30.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  276:             blk.30.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  280:             blk.31.attn_q.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:             blk.31.attn_k.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_v.weight q6_K     [  4096,  1024,     1,     1 ]
llama_model_loader: - tensor  283:        blk.31.attn_output.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  285:             blk.31.ffn_up.weight q6_K     [  4096, 14336,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_down.weight q6_K     [ 14336,  4096,     1,     1 ]
llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  289:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:                    output.weight q6_K     [  4096, 32002,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = ehartford_dolphin-2.1-mistral-7b
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  11:                          general.file_type u32              = 18
llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32002]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32002]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32002]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 32000
llama_model_loader: - kv  18:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q6_K:  226 tensors
llm_load_vocab: special tokens definition check successful ( 261/32002 ).
llm_load_print_meta: format           = GGUF V2
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32002
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_gqa            = 4
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             = 14336
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = mostly Q6_K
llm_load_print_meta: model params     = 7.24 B
llm_load_print_meta: model size       = 5.53 GiB (6.56 BPW) 
llm_load_print_meta: general.name   = ehartford_dolphin-2.1-mistral-7b
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 32000 '<|im_end|>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.11 MiB
llm_load_tensors: using ROCm for GPU acceleration
ggml_cuda_set_main_device: using device 0 (AMD Radeon RX 6800) as main device
llm_load_tensors: mem required  =  102.65 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 35/35 layers to GPU
llm_load_tensors: VRAM used: 5563.56 MiB
...................................................................................................
llama_new_context_with_model: n_ctx      = 4096
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama_kv_cache_init: offloading k cache to GPU
llama_kv_cache_init: VRAM kv self = 512.00 MiB
llama_new_context_with_model: kv self size  =  512.00 MiB
llama_build_graph: non-view tensors processed: 740/740
llama_new_context_with_model: compute buffer total size = 291.07 MiB
llama_new_context_with_model: VRAM scratch buffer: 288.00 MiB
llama_new_context_with_model: total VRAM used: 6363.57 MiB (model: 5563.56 MiB, context: 800.00 MiB)
AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
2023-12-27 22:30:22 INFO:LOADER: llama.cpp
2023-12-27 22:30:22 INFO:TRUNCATION LENGTH: 4096
2023-12-27 22:30:22 INFO:INSTRUCTION TEMPLATE: Alpaca
2023-12-27 22:30:22 INFO:Loaded the model in 2.43 seconds.
2023-12-27 22:30:34 INFO:Deleted logs/chat/Assistant/20231227-22-29-31.json.
Segmentation fault (core dumped)

The follow my loading settings:

[clemens98]

How do you run cublas on a AMD GPU? All I can find is ROCm supports cuda but in true amd fashion no mention on how it actually works

[userbox020]

How do you run cublas on a AMD GPU? All I can find is ROCm supports cuda but in true amd fashion no mention on how it actually works

sub bro, im not expert on cuda, rocm nor cublas, i just been digging on my free time these last weeks to make work my amd cards work with these new AI stuff. It doesnt use cublas, rocm uses hipBLAS and somehow not sure if i installed an extra ubuntu package but seems like hipBLAS somehow send data to CUDA, because you can use cuda env variables to set or disable gpus, also to test them with pythorch. However if i remember right, llamacpp doesnt use torch nor pythorch for backend

[clemens98]

sub bro, im not expert on cuda, rocm nor cublas, i just been digging on my free time these last weeks to make work my amd cards work with these new AI stuff. It doesnt use cublas, rocm uses hipBLAS and somehow not sure if i installed an extra ubuntu package but seems like hipBLAS somehow send data to CUDA, because you can use cuda env variables to set or disable gpus, also to test them with pythorch. However if i remember right, llamacpp doesnt use torch not pythorch for backend

Ty very much

[userbox020]

sup guys, I solve my problem compiling like the follow

make -j16 LLAMA_HIPBLAS=1 LLAMA_HIP_UMA=1 AMDGPU_TARGETS=gxf1030

Setting the follow environmental variables

export ROCM_PATH=/opt/rocm
export HCC_AMDGPU_TARGET=gfx1030
export HSA_OVERRIDE_GFX_VERSION=10.3.0

Now im able to run one rx 6900, two rx 6800 and one rx 6700 all together in multigpu. Everything working great now! but im using an old mobo with pcie x1 gen1 and take long time to load models, but when loaded the inference time its fast.

btw, im using rocm5.6