Мобильная версияЯ протестировал модель Mistral-7B -Instruct-v0.3.Q4_K_M.gguf и Mistral-7B-Instruct-v0.3.fp16.gguf в виртуальной машине с 32 виртуальными ЦП. Все модели ответили через 6–7 минут на запрос 15 000 токенов.
После этого я масштабирую виртуальную машину так, чтобы она имела 64 виртуальных ЦП, с теоретически наивным намерением улучшить время отклика модели. Я стремлюсь к тому, чтобы время ответа составляло 1–2 минуты.
Однако время ответа после увеличения количества виртуальных ЦП осталось прежним.
Ниже это мой тестовый скрипт Python:
Код: Выделить всё
from llama_cpp import Llama
import json
def test(model_path, n_threads_batch):
llm = Llama(model_path=model_path, n_ctx=32768, n_threads=64, n_threads_batch=n_threads_batch, offload_kqv=False)
with open("./message_sample.txt", "r", encoding="utf-8") as f:
messages = json.load(f)
resp = llm.create_chat_completion(messages=messages, temperature=0.0)
return resp
Код: Выделить всё
llama_model_loader: loaded meta data with 25 key-value pairs and 291 tensors from ./models/Mistral-7B-Instruct-v0.3.fp16.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 = llama
llama_model_loader: - kv 1: general.name str = models--mistralai--Mistral-7B-Instruc...
llama_model_loader: - kv 2: llama.block_count u32 = 32
llama_model_loader: - kv 3: llama.context_length u32 = 32768
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: llama.vocab_size u32 = 32768
llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
llama_model_loader: - kv 14: tokenizer.ggml.pre str = default
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32768] = ["", "", "", "[INST]", "[...
llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32768] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32768] = [2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 22: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 23: tokenizer.chat_template str = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv 24: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 226 tensors
llm_load_vocab: special tokens cache size = 1027
llm_load_vocab: token to piece cache size = 0.1731 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32768
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
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_ctx_orig_yarn = 32768
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = F16
llm_load_print_meta: model params = 7.25 B
llm_load_print_meta: model size = 13.50 GiB (16.00 BPW)
llm_load_print_meta: general.name = models--mistralai--Mistral-7B-Instruct-v0.3
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 = 781 ''
llm_load_print_meta: max token length = 48
llm_load_tensors: ggml ctx size = 0.14 MiB
llm_load_tensors: CPU buffer size = 13825.02 MiB
...................................................................................................
llama_new_context_with_model: n_ctx = 32768
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
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 = 4096.00 MiB
llama_new_context_with_model: KV self size = 4096.00 MiB, K (f16): 2048.00 MiB, V (f16): 2048.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.13 MiB
llama_new_context_with_model: CPU compute buffer size = 2144.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 1
AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD =
0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 |
Model metadata: {'tokenizer.chat_template': "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation r
oles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assis
tant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}", 'tokenizer.ggml.add_eos_token': 'fals
e', 'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.architecture': 'llama', 'l
lama.rope.freq_base': '1000000.000000', 'tokenizer.ggml.pre': 'default', 'llama.context_length': '32768', 'general.name': 'models--mistralai--Mistral-7B-Instruct-v0.3', 'tokenizer.ggml.
add_bos_token': 'true', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'tokenizer.ggml.bos_token_id': '1',
'llama.attention.head_count': '32', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8', 'general.file_type': '1', 'llama.vocab_size': '32768', 'llama.rope.dimension_count'
: '128'}
Available chat formats from metadata: chat_template.default
Guessed chat format: mistral-instruct
llama_print_timings: load time = 4449.01 ms
llama_print_timings: sample time = 59.17 ms / 332 runs ( 0.18 ms per token, 5610.57 tokens per second)
llama_print_timings: prompt eval time = 363534.49 ms / 18814 tokens ( 19.32 ms per token, 51.75 tokens per second)
llama_print_timings: eval time = 66030.23 ms / 331 runs ( 199.49 ms per token, 5.01 tokens per second)
llama_print_timings: total time = 430140.04 ms / 19145 tokens
Подробнее здесь: https://stackoverflow.com/questions/787 ... unning-llm
