search

SciSharp / LLamaSharp

A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
https://scisharp.github.io/LLamaSharp
MIT License
2.49k stars 332 forks source link

'The type initializer for 'LLama.Native.NativeApi' threw an exception' in MAUI App #180

Open nappa0326 opened 12 months ago

nappa0326 commented 12 months ago

I thought the problem was similar to #58, but I could not solve it with that issue's solution.

First, I added the following source to the constructor of the MAUI App's MainPage.xaml.cs created in the wizard.

string modelPath = "{model_path}"

// Load model
var parameters = new ModelParams(modelPath)
{
    ContextSize = 2048,
    Seed = 1337,
    GpuLayerCount = 5,
};

using var model = LLamaWeights.LoadFromFile(parameters);
using var context = model.CreateContext(parameters);
var ex = new InteractiveExecutor(context);
ChatSession session = new ChatSession(ex);

Then, execute this application, the following exception is occurred.

System.TypeInitializationException HResult=0x80131534 Message=The type initializer for 'LLama.Native.NativeApi' threw an exception. Source=LLamaSharp

RuntimeError: The native library cannot be found. It could be one of the following reasons:

  1. No LLamaSharp backend was installed. Please search LLamaSharp.Backend and install one of them.
  2. You are using a device with only CPU but installed cuda backend. Please install cpu backend instead.
  3. The backend is not compatible with your system cuda environment. Please check and fix it. If the environment is expected not to be changed, then consider build llama.cpp from source or submit an issue to LLamaSharp.
  4. One of the dependency of the native library is missed.

The environment is as follows.

Windows11 [Version 10.0.22621.2283] maui-windows 7.0.92/7.0.100 VS 17.7.34031.279 LLamaSharp 0.5.1 LLamaSharp.Backend.Cuda12 0.5.1

スクリーンショット 2023-09-23 140214

Note that the above source works fine when implement into a console application created by VS2022 wizard in the same environment. The following is the output of that application.

_ggml_init_cublas: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6 llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from C:\Users\nappa\AppData\Local\Packages\91f0e9ee-d8fd-40e7-b386-4f48ff88f821_jmyq9vndw01x8\LocalState\llama-2-7b-guanaco-qlora.Q5_K_M.gguf (version GGUF V2 (latest)) llama_model_loader: - tensor 0: token_embd.weight q5_K [ 4096, 32000, 1, 1 ] llama_model_loader: - tensor 1: blk.0.attn_q.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 2: blk.0.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 3: blk.0.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 4: blk.0.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 5: blk.0.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 6: blk.0.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 7: blk.0.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 11: blk.1.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 12: blk.1.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 13: blk.1.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 14: blk.1.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 15: blk.1.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 16: blk.1.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 20: blk.2.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 21: blk.2.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 22: blk.2.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 23: blk.2.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 24: blk.2.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 25: blk.2.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 29: blk.3.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 30: blk.3.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 31: blk.3.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 32: blk.3.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 33: blk.3.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 34: blk.3.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 38: blk.4.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 39: blk.4.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 40: blk.4.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 41: blk.4.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 42: blk.4.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 43: blk.4.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 47: blk.5.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 48: blk.5.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 49: blk.5.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 50: blk.5.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 51: blk.5.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 52: blk.5.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 56: blk.6.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 57: blk.6.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 58: blk.6.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 59: blk.6.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 60: blk.6.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 61: blk.6.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 65: blk.7.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 66: blk.7.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 67: blk.7.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 68: blk.7.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 69: blk.7.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 70: blk.7.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 74: blk.8.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 75: blk.8.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 76: blk.8.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 77: blk.8.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 78: blk.8.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 79: blk.8.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 83: blk.9.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 84: blk.9.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 85: blk.9.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 86: blk.9.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 87: blk.9.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 88: blk.9.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 92: blk.10.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 93: blk.10.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 94: blk.10.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 95: blk.10.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 96: blk.10.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 97: blk.10.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 101: blk.11.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 102: blk.11.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 103: blk.11.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 104: blk.11.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 105: blk.11.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 106: blk.11.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 110: blk.12.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 111: blk.12.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 112: blk.12.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 113: blk.12.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 114: blk.12.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 115: blk.12.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 119: blk.13.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 120: blk.13.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 121: blk.13.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 122: blk.13.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 123: blk.13.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 124: blk.13.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 128: blk.14.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 129: blk.14.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 130: blk.14.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 131: blk.14.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 132: blk.14.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 133: blk.14.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 137: blk.15.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 138: blk.15.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 139: blk.15.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 140: blk.15.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 141: blk.15.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 142: blk.15.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 146: blk.16.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 147: blk.16.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 148: blk.16.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 149: blk.16.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 150: blk.16.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 151: blk.16.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 155: blk.17.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 156: blk.17.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 157: blk.17.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 158: blk.17.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 159: blk.17.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 160: blk.17.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 164: blk.18.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 165: blk.18.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 166: blk.18.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 167: blk.18.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 168: blk.18.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 169: blk.18.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 173: blk.19.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 174: blk.19.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 175: blk.19.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 176: blk.19.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 177: blk.19.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 178: blk.19.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 182: blk.20.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 183: blk.20.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 184: blk.20.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 185: blk.20.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 186: blk.20.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 187: blk.20.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 191: blk.21.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 192: blk.21.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 193: blk.21.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 194: blk.21.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 195: blk.21.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 196: blk.21.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 200: blk.22.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 201: blk.22.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 202: blk.22.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 203: blk.22.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 204: blk.22.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 205: blk.22.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 209: blk.23.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 210: blk.23.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 211: blk.23.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 212: blk.23.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 213: blk.23.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 214: blk.23.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 218: blk.24.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 219: blk.24.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 220: blk.24.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 221: blk.24.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 222: blk.24.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 223: blk.24.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 227: blk.25.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 228: blk.25.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 229: blk.25.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 230: blk.25.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 231: blk.25.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 232: blk.25.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 236: blk.26.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 237: blk.26.attn_v.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 238: blk.26.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 239: blk.26.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 240: blk.26.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 241: blk.26.ffn_down.weight q5_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 245: blk.27.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 246: blk.27.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 247: blk.27.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 248: blk.27.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 249: blk.27.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 250: blk.27.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 254: blk.28.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 255: blk.28.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 256: blk.28.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 257: blk.28.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 258: blk.28.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 259: blk.28.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 263: blk.29.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 264: blk.29.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 265: blk.29.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 266: blk.29.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 267: blk.29.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 268: blk.29.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 272: blk.30.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 273: blk.30.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 274: blk.30.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 275: blk.30.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 276: blk.30.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 277: blk.30.ffn_down.weight q6_K [ 11008, 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 q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 281: blk.31.attn_k.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 282: blk.31.attn_v.weight q6_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 283: blk.31.attn_output.weight q5_K [ 4096, 4096, 1, 1 ] llama_model_loader: - tensor 284: blk.31.ffn_gate.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 285: blk.31.ffn_up.weight q5_K [ 4096, 11008, 1, 1 ] llama_model_loader: - tensor 286: blk.31.ffn_down.weight q6_K [ 11008, 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, 32000, 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 q5_K: 193 tensors llama_model_loader: - type q6_K: 33 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 = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 2048 llm_load_print_meta: n_ctx = 2048 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 = 1.0e-05 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: n_ff = 11008 llm_load_print_meta: freq_base = 10000.0 llm_load_print_meta: freq_scale = 1 llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = mostly Q5_K - Medium llm_load_print_meta: model size = 6.74 B llm_load_print_meta: general.name = mikael110_llama-2-7b-guanaco-fp16 llm_load_print_meta: BOS token = 1 '' llm_load_print_meta: EOS token = 2 '' llm_load_print_meta: UNK token = 0 '' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.09 MB llm_load_tensors: using CUDA for GPU acceleration llm_load_tensors: mem required = 3858.18 MB (+ 1024.00 MB per state) llm_load_tensors: offloading 5 repeating layers to GPU llm_load_tensors: offloaded 5/35 layers to GPU llm_load_tensors: VRAM used: 703 MB .................................................................................................. llama_new_context_with_model: kv self size = 1024.00 MB llama_new_context_with_model: compute buffer total size = 153.41 MB llama_new_context_withmodel: VRAM scratch buffer: 152.00 MB

AsakusaRinne commented 11 months ago

I'm not familiar with MAUI but I'd like to help you with it. Could you please search the libllama file in your bin folder of MAUI? (I assume that there's a folder containing all things necessary for running MAUI app)

nappa0326 commented 11 months ago

@AsakusaRinne I found the 'libllama.dll' file in the bin folder ('bin\Debug\net7.0-windows10.0.19041.0\win10-x64') when using either 'LLamaSharp.Backend.Cuda12' or 'LLamaSharp.Backend.Cpu'.

The exceptions that occurred were the same in both cases.

Thank you.

AsakusaRinne commented 10 months ago

Recently it's a common issue that using backend packages on machine without avx2 support will have this error. Could you please check if your PC support avx2?

lcarrere commented 9 months ago

I can confirm that running CUDA version on MAUI, so on Windows operating system, can't work with the current implementation. As MAUI apps run in a sandbox the native libraries search will not honor the system Path environment variable. Therefore llama.cpp will fail to be initialized, as it requires resolution of the CUDA SDK.

To me there are 2 options:

1/

2/

replace:

if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
    cudaPath = Environment.GetEnvironmentVariable("CUDA_PATH");
    if (cudaPath is null)
    {
        return -1;
    }
    version = GetCudaVersionFromPath(cudaPath);
}

by

if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
    cudaPath = Environment.GetEnvironmentVariable("CUDA_PATH");
    if (cudaPath is null)
    {
        return -1;
    }

   //Ensuring cuda bin path is reachable. Especially for MAUI environment.
   string cudaBinPath = Path.Combine(cudaPath, "bin");

   if (Directory.Exists(cudaBinPath))
   {
       AddDllDirectory(cudaBinPath);
   }

    version = GetCudaVersionFromPath(cudaPath);
}

The AddDllDirectory definition:

    internal static class LocalGGUFRuntime
    {
        [DllImport("kernel32.dll", CharSet = CharSet.Unicode, SetLastError = true)]
        private static extern int AddDllDirectory(string NewDirectory);
AsakusaRinne commented 9 months ago

@lcarrere In v0.8.0 we added cpu and cuda feature detections, along with an API to let you specify the path of library yourself. As you mentioned, the MAUI app may have different behaviors of native library searching, could you please use NativeLibraryConfig.Default.WithLibrary({YOUR_PATH}) to specify the path of the native library you want to load?

Note that the code above should be added before any llama model is initialized. We strongly recommend to put it at the very beginning of your code.

if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
    cudaPath = Environment.GetEnvironmentVariable("CUDA_PATH");
    if (cudaPath is null)
    {
        return -1;
    }

   //Ensuring cuda bin path is reachable. Especially for MAUI environment.
   string cudaBinPath = Path.Combine(cudaPath, "bin");

   if (Directory.Exists(cudaBinPath))
   {
       AddDllDirectory(cudaBinPath);
   }

    version = GetCudaVersionFromPath(cudaPath);
}

If it works for you, we'd like to add it to LLamaSharp. :)

lcarrere commented 9 months ago

@AsakusaRinne NativeLibraryConfig.Instance.WithLibrary() is working. Though it's not mandatory to use it to get MAUI working with automatic backend loading + CUDA runtime loading, with the patch I suggested.

To be clear: adding my patch, makes MAUI working using the default backend loading. It is only intended to allow the current process to resolves native DLLs of the CUDA runtime.

Let me know if i am not clear enough.

AsakusaRinne commented 9 months ago

@AsakusaRinne NativeLibraryConfig.Instance.WithLibrary() is working. Though it's not mandatory to use it to get MAUI working with automatic backend loading + CUDA runtime loading, with the patch I suggested.

To be clear: adding my patch, makes MAUI working using the default backend loading. It is only intended to allow the current process to resolves native DLLs of the CUDA runtime.

Let me know if i am not clear enough.

Thank you for your feedback. There're the following questions confusing me:

  1. If a user has had cuda installed on windows and is able to run cuda based code, is MAUI still possible not able to take take use of cuda unless some specific settings?
  2. When you publish your MAUI app, is it acceptable to contain more than one native libraries? And when the user install the app, is it possible to put the files into a specified path?
  3. As a MAUI developer, what is the best way for you to develop and publish a MAUI app? (you're not supposed to take feasibility into account)

In fact I've long been planning to add an integration or example for MAUI because it's the most popular cross-platform UI in .NET. It has been on the TODO list of this repo since the beginning. However I don't have much knowledge about it and time was limited for me in the past 3 months so that I didn't even start it. At least, I'll do something to make it more convenient for MAUI developers to use LLamaSharp. :)

lcarrere commented 9 months ago

If a user has had cuda installed on windows and is able to run cuda based code, is MAUI still possible not able to take take use of cuda unless some specific settings?

It depends on the deployment strategy.

1- If the application is deployed expecting the CUDA Toolkit being installed on the platform: Developer have to ensure that CUDA runtime path is included into the set of directories that are searched by the Windows native library lookup mechanism. As MAUI apps run in a sandbox mode, ones defined by the PATH environment variable will be ignored. Since the default llama.cpp runtime loading strategy of LlamaSharp is based on the system configuration, I would say LlamaSharp endorses the "responsibility" to ensure the correct CUDA runtime is reachable.

2- If the application is deployed by including all required runtimes: It's up to the application developer to guaranty the availability of these runtimes into the application bin path. This is trickier and probably implies legal constraints. By allowing custom runtime loading in latest code base, I would say you've opened the pandora box :) Because in this mode, you can not determine, from llamaSharp, which CUDA runtime has been used to compile the llama.cpp backend. So technically, you should also allow the calling app, for Windows, to specify the CUDA runtime path that the backend is compatible with.

When you publish your MAUI app, is it acceptable to contain more than one native libraries?

Sure.

And when the user install the app, is it possible to put the files into a specified path?

Yes.

As a MAUI developer, what is the best way for you to develop and publish a MAUI app? (you're not supposed to take feasibility into account)

I have no much expertise on MAUI. But I would say that developer expectations would be to be able to consume components without having to implement any platform specific logic. I would consider LLamaSharp as a reusable component, compatible with MacOS and Windows.

That being said, I see 2 major deployment models:

1- One implying the constraint that for running on Windows OS, the CUDA runtime must be installed on the system. This is the scenario LLamaSharp currently fails to address, but easily resolvable with the approach I'm suggesting.

2- One implying that all runtime are managed/shipped within the deployed app. Just a guess: I believe the CUDA runtime must be shipped within the application package, which runtime must be compatible with llama.cpp backend consumed by LLamaSharp. -> Therefore using the new .WithLibrary() method.

And for debugging and prototyping purposes, I would say the first scenario is mandatory to cover.

So, to sum up: LLamaSharp implements an automatic backend loading mechanism based on the OS configuration (referring to the CUDA_PATH environment variable you're parsing). For it to consistently work within MAUI on Windows, it should also guarantee that the BIN files located within this retrieved path are reachable by the loadLibrary* Windows API, which will be used under the hood during the llama.cpp backend loading.

Let me know if you need further clarification or any test from my end.

evolcano commented 6 months ago

@AsakusaRinne Yes! It works in MAUI of my windows 11! Please add it to LLamaSharp.

Thanks you , @lcarrere

AsakusaRinne commented 6 months ago

@evolcano Glad to hear that LLamaSharp works well with MAUI! I'm sorry that I'm not familiar with MAUI and don't have much time to study it yet. I won't reject a PR if you'd like to add an integration or an example for it. :)

AmSmart commented 4 months ago

@AsakusaRinne Hasn't this issue been fixed by #631. I think it can be closed now