hipBlas and ROCm #1214

Dimashaman · 2023-11-12T12:55:46Z

Dimashaman
Nov 12, 2023

Have anybody managed to launch PrivateGPT on Windows with AMD ROCm technology? Because I wasted a day trying

bursica · 2023-11-12T15:08:31Z

bursica
Nov 12, 2023

It would b great for AMD support also for Ubuntu 22.04., for us less fortunate.

Was trying unsucesfully with:
CMAKE_ARGS='-DLLAMA_HIPBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python

1 reply

pabloogc Nov 12, 2023
Maintainer

Can't help with this sadly, nobody in the team has a AMD gpu AFAIK. I'll leave the issue open, maybe someone made it work.

Dimashaman · 2023-11-13T07:39:48Z

Dimashaman
Nov 13, 2023
Author

Ok I've desided to waste another day and managed to run PrivateGPT on WIndows 10 using HIPBLAS=1. I used MINGW64 command line interface that goes together with git installation "Git Bash"

CMAKE_ARGS='-G Ninja -DCMAKE_BUILD_TYPE=Release -DLLAMA_HIPBLAS=on -DCMAKE_C_COMPILER=clang.exe -DCMAKE_CXX_COMPILER=clang++.exe -DAMDGPU_TARGETS=gfx1030' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python this is the command that worked. Before that I added lots of ENVs like

C:\Program Files\Microsoft Visual Studio\2022\Community\Common7\IDE\CommonExtensions\Microsoft\CMake\CMake\bin
C:\Program Files\Microsoft Visual Studio\2022\Community\Common7\IDE\CommonExtensions\Microsoft\CMake\Ninja
C:\Strawberry\perl\bin
C:\Program Files\AMD\ROCm\5.5\bin
C:\Program Files\Go\bin
I also had FORCE_CMAKE = 1,
CC = 'C:\Program Files\AMD\ROCm\5.5\bin\clang.exe',
CCX = 'C:\Program Files\AMD\ROCm\5.5\bin\clang++.exe'
envs.

Dima@DimaPc MINGW64 /e/privateGPT (main)
$ CMAKE_ARGS='-G Ninja -DCMAKE_BUILD_TYPE=Release -DLLAMA_HIPBLAS=on -DCMAKE_C_COMPILER=clang.exe -DCMAKE_CXX_COMPILER=clang++.exe -DAMDGPU_TARGETS=gfx1030' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python
Collecting llama-cpp-python
  Downloading llama_cpp_python-0.2.17.tar.gz (7.8 MB)
     ---------------------------------------- 7.8/7.8 MB 4.1 MB/s eta 0:00:00
  Installing build dependencies: started
  Installing build dependencies: finished with status 'done'
  Getting requirements to build wheel: started
  Getting requirements to build wheel: finished with status 'done'
  Preparing metadata (pyproject.toml): started
  Preparing metadata (pyproject.toml): finished with status 'done'
Collecting typing-extensions>=4.5.0 (from llama-cpp-python)
  Downloading typing_extensions-4.8.0-py3-none-any.whl.metadata (3.0 kB)
Collecting numpy>=1.20.0 (from llama-cpp-python)
  Downloading numpy-1.26.2-cp311-cp311-win_amd64.whl.metadata (61 kB)
     ---------------------------------------- 61.2/61.2 kB ? eta 0:00:00
Collecting diskcache>=5.6.1 (from llama-cpp-python)
  Downloading diskcache-5.6.3-py3-none-any.whl.metadata (20 kB)
Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)
   ---------------------------------------- 45.5/45.5 kB ? eta 0:00:00
Downloading numpy-1.26.2-cp311-cp311-win_amd64.whl (15.8 MB)
   ---------------------------------------- 15.8/15.8 MB 6.7 MB/s eta 0:00:00
Downloading typing_extensions-4.8.0-py3-none-any.whl (31 kB)
Building wheels for collected packages: llama-cpp-python
  Building wheel for llama-cpp-python (pyproject.toml): started
  Building wheel for llama-cpp-python (pyproject.toml): finished with status 'done'
  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.17-cp311-cp311-win_amd64.whl size=38256098 sha256=17086d473498989a5464d7bc0717650691ae8ff597603eb08ddc5b6efbfc391b
  Stored in directory: C:\Users\Dima\AppData\Local\Temp\pip-ephem-wheel-cache-mhd_tfxd\wheels\36\fa\c0\325f5c14c1c1703130b5330439e6109f84854017b04b34d333
Successfully built llama-cpp-python
Installing collected packages: typing-extensions, numpy, diskcache, llama-cpp-python
  Attempting uninstall: typing-extensions
    Found existing installation: typing_extensions 4.8.0
    Uninstalling typing_extensions-4.8.0:
      Successfully uninstalled typing_extensions-4.8.0
  Attempting uninstall: numpy
    Found existing installation: numpy 1.26.2
    Uninstalling numpy-1.26.2:
      Successfully uninstalled numpy-1.26.2
  Attempting uninstall: diskcache
    Found existing installation: diskcache 5.6.3
    Uninstalling diskcache-5.6.3:
      Successfully uninstalled diskcache-5.6.3
  Attempting uninstall: llama-cpp-python
    Found existing installation: llama_cpp_python 0.2.17
    Uninstalling llama_cpp_python-0.2.17:
      Successfully uninstalled llama_cpp_python-0.2.17
Successfully installed diskcache-5.6.3 llama-cpp-python-0.2.17 numpy-1.26.2 typing-extensions-4.8.0

Dima@DimaPc MINGW64 /e/privateGPT (main)
$ PGPT_PROFILES=local make run
poetry run python -m private_gpt
18:27:42.171 [INFO    ] private_gpt.settings.settings_loader - Starting application with profiles=['default', 'local']
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 ROCm devices:
  Device 0: AMD Radeon RX 6800, compute capability 10.3
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from E:\privateGPT\models\llama-2-7b-chat.Q4_K_M.gguf (version GGUF V2)
llama_model_loader: - tensor    0:                token_embd.weight q4_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    8:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   17:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   24:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   26:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   27:             blk.10.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   33:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   35:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   36:             blk.11.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   42:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   44:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   45:             blk.12.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   51:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   53:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   54:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   60:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   62:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   63:             blk.14.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   69:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   71:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   72:             blk.15.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   78:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   80:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   81:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   87:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   89:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   90:             blk.17.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   96:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   98:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.18.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  105:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  107:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  114:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  116:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  117:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  123:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  125:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  132:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  134:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.21.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  141:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  143:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.22.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  150:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  152:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  159:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  161:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  162:              blk.3.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  168:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  170:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  171:              blk.4.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  177:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  179:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  180:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  186:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  188:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  189:              blk.6.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  195:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  197:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  198:              blk.7.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  204:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  206:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  207:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  213:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  215:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  216:              blk.9.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  223:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  224:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  226:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  232:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  233:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  235:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  241:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  242:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  244:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  250:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  251:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  253:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  259:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  260:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  262:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  268:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  269:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  271:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  277:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  278:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  280:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  286:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  287:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  289:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  290:               output_norm.weight f32      [  4096,     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:                          general.file_type u32
llama_model_loader: - kv  11:                       tokenizer.ggml.model str
llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr
llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv  18:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_K:  193 tensors
llama_model_loader: - type q6_K:   33 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
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          = 32000
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 4096
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 32
llm_load_print_meta: n_layer          = 32
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-06
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             = 11008
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  = 4096
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = mostly Q4_K - Medium
llm_load_print_meta: model params     = 6.74 B
llm_load_print_meta: model size       = 3.80 GiB (4.84 BPW)
llm_load_print_meta: general.name   = LLaMA v2
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 =    0.11 MB
llm_load_tensors: using ROCm for GPU acceleration
llm_load_tensors: mem required  =   70.42 MB
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: 3820.93 MB
..................................................................................................
llama_new_context_with_model: n_ctx      = 3900
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 = 1950.00 MB
llama_new_context_with_model: kv self size  = 1950.00 MB
llama_build_graph: non-view tensors processed: 740/740
llama_new_context_with_model: compute buffer total size = 282.00 MB
llama_new_context_with_model: VRAM scratch buffer: 275.37 MB
llama_new_context_with_model: total VRAM used: 6046.30 MB (model: 3820.93 MB, context: 2225.37 MB)
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 |

Sad thing is that... it works really slow in the web interface,
i typed hello, my friend in PrivateGPT web interface and got

llama_print_timings:        load time =    5378.15 ms
llama_print_timings:      sample time =      31.68 ms /    10 runs   (    3.17 ms per token,   315.70 tokens per second)
llama_print_timings: prompt eval time =    5361.78 ms /   436 tokens (   12.30 ms per token,    81.32 tokens per second)
llama_print_timings:        eval time =   14284.24 ms /     9 runs   ( 1587.14 ms per token,     0.63 tokens per second)
llama_print_timings:       total time =   22301.99 ms

log after Ctrl+C

if I load the same model using https://github.com/YellowRoseCx/koboldcpp-rocm/releases/download/1.48.1.yr2-ROCm/koboldcpp_rocm_only.exe
it runs much much faster

Processing Prompt [BLAS] (424 / 424 tokens)
Generating (5 / 250 tokens)
(EOS token triggered!)
ContextLimit: 429/1600, Processing:0.45s (1.1ms/T), Generation:0.07s (14.4ms/T), Total:0.52s (9.63T/s)
Output:  Greetings.

0 replies

Shymxll · 2023-11-13T13:39:27Z

Shymxll
Nov 13, 2023

İt is great

0 replies

bursica · 2023-11-13T20:55:22Z

bursica
Nov 13, 2023

Ubuntu successfull 2

...work in progress, suggestions welcome :)

Install

Install ROCm:
sudo apt update
sudo apt install rocm-dev rocm-libs rocm-utils
Install CMake, Ninja:
sudo apt install cmake ninja-build
Just to make sure you have python 3.11 and python-dev (don't make it default, if system-wide):
sudo apt install python3.11
sudo apt-get install python3-dev

env in .bashrc:

export CMAKE_PREFIX_PATH=/opt/rocm
export PATH=/opt/rocm/bin:$PATH

export ROCM_PATH=/opt/rocm-5.7.1
export HIP_PATH=$ROCM_PATH
export PATH=$ROCM_PATH/bin:$PATH
export PATH=$HIP_PATH/bin:$PATH
export LD_LIBRARY_PATH=$ROCM_PATH/lib:$LD_LIBRARY_PATH

export CC=/usr/bin/amdclang
export CXX=/usr/bin/amdclang++
export FORCE_CMAKE=1

Build

CMAKE_ARGS='-G Ninja -DLLAMA_HIPBLAS=on -DCMAKE_C_COMPILER=amdclang -DCMAKE_CXX_COMPILER=amdclang++ -DAMDGPU_TARGETS=gfx1030' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python

Note: DAMDGPU_TARGETS=gfx1030 ...RDNA2 (e.g. 6000 series)

Result

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 |

7 replies

bursica Nov 14, 2023

Some Results

on mistral-7b-instruct-v0.1.Q4_K_M.gguf
llama_print_timings: load time = 173.41 ms
llama_print_timings: sample time = 4.82 ms / 10 runs ( 0.48 ms per token, 2074.26 tokens per second)
llama_print_timings: prompt eval time = 168.19 ms / 38 tokens ( 4.43 ms per token, 225.93 tokens per second)
llama_print_timings: eval time = 271.25 ms / 9 runs ( 30.14 ms per token, 33.18 tokens per second)
llama_print_timings: total time = 860.51 ms
on zephyr-7b-beta.Q4_K_M.gguf
llama_print_timings: load time = 172.52 ms
llama_print_timings: sample time = 119.72 ms / 256 runs ( 0.47 ms per token, 2138.41 tokens per second)
llama_print_timings: prompt eval time = 167.34 ms / 38 tokens ( 4.40 ms per token, 227.09 tokens per second)
llama_print_timings: eval time = 5939.67 ms / 255 runs ( 23.29 ms per token, 42.93 tokens per second)
llama_print_timings: total time = 30139.97 ms
on llama-2-7b-chat.Q4_K_M.gguf
llama_print_timings: load time = 144.79 ms
llama_print_timings: sample time = 13.57 ms / 28 runs ( 0.48 ms per token, 2063.07 tokens per second)
llama_print_timings: prompt eval time = 139.58 ms / 39 tokens ( 3.58 ms per token, 279.41 tokens per second)
llama_print_timings: eval time = 636.81 ms / 27 runs ( 23.59 ms per token, 42.40 tokens per second)
llama_print_timings: total time = 2105.94 ms

I would still enjoy the option of connecting to other locally running LLM's: #1217

dimashaman47 Nov 14, 2023

It looks like your time is less then a second, while mine is 22 seconds and I don't understand why.. Something is wrong

bursica Nov 14, 2023

You should look tokens/second, since total time depents on how model behaves when answering (long/short).
Additionally in ubuntu there are compilers within ROCm installation folder amdclang, amdclang++, since using just system-wide installation of clang and clang++ throws error when compiling.
Another issue may arise from hardware itself, in my case theardripper + 6900XT, some other HW may establish bottlenecks.

Dimashaman Nov 15, 2023
Author

what is your cpu consumption? Mine is less than 20% (17-18) while answering, I have 13400f intel i5

bursica Nov 17, 2023

overall below 2%.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

hipBlas and ROCm #1214

{{title}}

Replies: 4 comments 8 replies

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{title}}

{{title}}

Select a reply

hipBlas and ROCm #1214

Replies: 4 comments · 8 replies

pabloogc Nov 12, 2023 Maintainer

Dimashaman Nov 13, 2023 Author

Ubuntu successfull 2

Install

env in .bashrc:

Build

Result

Some Results

Dimashaman Nov 15, 2023 Author

Replies: 4 comments 8 replies

pabloogc Nov 12, 2023
Maintainer

Dimashaman
Nov 13, 2023
Author

Dimashaman Nov 15, 2023
Author