Windows 使用 qwen2 无法设置 GPU 使用

[allanpk716]

System Info / 系統信息

cuda 11.8
llama-cpp-python 0.2.55
python 3.10
windows 10

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

0.14.0

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local

Reproduction / 复现过程

2024-08-05 20:41:08,332 xinference.core.worker 146864 INFO You specify to launch the model: qwen2-instruct on GPU index: [0] of the worker: 127.0.0.1:59241, xinference will automatically ignore the n_gpu option.
2024-08-05 20:41:24,186 xinference.model.llm.llm_family 146864 INFO Caching from Modelscope: qwen/Qwen2-7B-Instruct-GGUF
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from C:\Users\allan716.cache\modelscope\hub\qwen\Qwen2-7B-Instruct-GGUF\qwen2-7b-instruct-q4_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = qwen2
llama_model_loader: - kv 1: general.name str = qwen2-7b-instruct
llama_model_loader: - kv 2: qwen2.block_count u32 = 28
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 10: general.file_type u32 = 2
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 19: tokenizer.chat_template str = {% for message in messages %}{% if lo...
llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - kv 22: quantize.imatrix.file str = ../Qwen2/gguf/qwen2-7b-imatrix/imatri...
llama_model_loader: - kv 23: quantize.imatrix.dataset str = ../sft_2406.txt
llama_model_loader: - kv 24: quantize.imatrix.entries_count i32 = 196
llama_model_loader: - kv 25: quantize.imatrix.chunks_count i32 = 1937
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q4_0: 194 tensors
llama_model_loader: - type q4_1: 3 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 421/152064 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = qwen2
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 152064
llm_load_print_meta: n_merges = 151387
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 3584
llm_load_print_meta: n_head = 28
llm_load_print_meta: n_head_kv = 4
llm_load_print_meta: n_layer = 28
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 = 7
llm_load_print_meta: n_embd_k_gqa = 512
llm_load_print_meta: n_embd_v_gqa = 512
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 = 18944
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 2
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 1000000.0
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 = ?B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 7.62 B
llm_load_print_meta: model size = 4.13 GiB (4.66 BPW)
llm_load_print_meta: general.name = qwen2-7b-instruct
llm_load_print_meta: BOS token = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token = 151645 '<|im_end|>'
llm_load_print_meta: PAD token = 151643 '<|endoftext|>'
llm_load_print_meta: LF token = 30 '?'
llm_load_tensors: ggml ctx size = 0.13 MiB
Exception ignored on calling ctypes callback function: <function llama_log_callback at 0x00000259E17AFD90>
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\xin\lib\site-packages\llama_cpp_logger.py", line 30, in llama_log_callback
print(text.decode("utf-8"), end="", flush=True, file=sys.stderr)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc4 in position 90: invalid continuation byte
llm_load_tensors: CPU buffer size = 4232.57 MiB
......................................................................................
llama_new_context_with_model: n_ctx = 32768
llama_new_context_with_model: freq_base = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CPU KV buffer size = 1792.00 MiB
llama_new_context_with_model: KV self size = 1792.00 MiB, K (f16): 896.00 MiB, V (f16): 896.00 MiB
llama_new_context_with_model: CPU input buffer size = 72.26 MiB
llama_new_context_with_model: CPU compute buffer size = 1806.00 MiB
llama_new_context_with_model: graph splits (measure): 1
AVX = 1 | AVX_VNNI = 0 | 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 = 0 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 |
Model metadata: {'qwen2.attention.head_count': '28', 'general.name': 'qwen2-7b-instruct', 'general.architecture': 'qwen2', 'qwen2.block_count': '28', 'qwen2.context_length': '32768', 'qwen2.attention.head_count_kv': '4', 'quantize.imatrix.dataset': '../sft_2406.txt', 'qwen2.embedding_length': '3584', 'general.quantization_version': '2', 'tokenizer.ggml.bos_token_id': '151643', 'qwen2.feed_forward_length': '18944', 'tokenizer.ggml.padding_token_id': '151643', 'qwen2.rope.freq_base': '1000000.000000', 'qwen2.attention.layer_norm_rms_epsilon': '0.000001', 'tokenizer.ggml.eos_token_id': '151645', 'general.file_type': '2', 'tokenizer.ggml.model': 'gpt2', 'tokenizer.ggml.pre': 'qwen2', 'tokenizer.chat_template': "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", 'tokenizer.ggml.add_bos_token': 'false', 'quantize.imatrix.chunks_count': '1937', 'quantize.imatrix.file': '../Qwen2/gguf/qwen2-7b-imatrix/imatrix.dat', 'quantize.imatrix.entries_count': '196'}
Using gguf chat template: {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
You are a helpful assistant.<|im_end|>
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}
Using chat eos_token: <|im_end|>
Using chat bos_token: <|endoftext|>

Expected behavior / 期待表现

能够使用 GPU 执行 qwen2 的推理任务

[ldqrecord]

+1,llama-3.1 gguf模型以及本地注册gguf模型 ，无法使用gpu运行，torch 2.01+cu11.8