直接安装,只支持CPU。想支持GPU,贫苦一些。
1. 安装CUDA Toolkit (NVIDIA CUDA Toolkit (available at https://developer.nvidia.com/cuda-downloads)
2. 安装如下物件:
- git
- python
- cmake
- Visual Studio Community (make sure you install this with the following settings)
- Desktop development with C++
- development
- Linux embedded development with C++
3. Clone git repository recursively to get llama.cpp submodule as well
git clone --recursive -j8 https://github.com/abetlen/llama-cpp-python.git
4. Open up a command Prompt and set the following environment variables.
- set FORCE_CMAKE=1
- set CMAKE_ARGS=-DLLAMA_CUBLAS=ON
复制代码 5. 复制文件从Cuda到VS:**
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.3\extras\visual_studio_integration\MSBuildExtensions下面有四个文件,全部copy。
然后复制到:
C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations下面。
6. Compiling and installing
- cd\llama-cpp-python
- python -m pip install -e .
复制代码 7. 检查成果:
- >>> from llama_cpp import Llama
- >>> llm = Llama(model_path="llama-2-7b-chat.Q8_0.gguf",n_gpu_layers=-1)
复制代码 结果:
- ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
- ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
- ggml_init_cublas: found 1 CUDA devices:
- Device 0: NVIDIA GeForce RTX 4090, compute capability 6.1, VMM: yes
- llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from llama-2-7b-chat.Q8_0.gguf (version GGUF V2)
- llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
- llama_model_loader: - kv 0: general.architecture str = llama
- llama_model_loader: - kv 1: general.name str = LLaMA v2
- llama_model_loader: - kv 2: llama.context_length u32 = 4096
- 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 = 11008
- 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 = 32
- llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000001
- llama_model_loader: - kv 10: general.file_type u32 = 7
- llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
- llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
- llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
- llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
- llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
- llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
- llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32 = 0
- llama_model_loader: - kv 18: general.quantization_version u32 = 2
- llama_model_loader: - type f32: 65 tensors
- llama_model_loader: - type q8_0: 226 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_embd_head_k = 128
- llm_load_print_meta: n_embd_head_v = 128
- llm_load_print_meta: n_gqa = 1
- llm_load_print_meta: n_embd_k_gqa = 4096
- llm_load_print_meta: n_embd_v_gqa = 4096
- 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: n_expert = 0
- llm_load_print_meta: n_expert_used = 0
- 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 = Q8_0
- llm_load_print_meta: model params = 6.74 B
- llm_load_print_meta: model size = 6.67 GiB (8.50 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>'
复制代码 显卡终于在列,可以玩儿了。
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。 |