{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/limeng/anaconda3/envs/Qwen2.5/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n", "2025-03-19 13:23:29,599\tINFO util.py:154 -- Missing packages: ['ipywidgets']. Run `pip install -U ipywidgets`, then restart the notebook server for rich notebook output.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO 03-19 13:23:37 config.py:350] This model supports multiple tasks: {'generate', 'embedding'}. Defaulting to 'generate'.\n", "WARNING 03-19 13:23:37 config.py:428] gptq quantization is not fully optimized yet. The speed can be slower than non-quantized models.\n", "INFO 03-19 13:23:37 llm_engine.py:249] Initializing an LLM engine (v0.6.4.post1) with config: model='/opt/lung/llm/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', speculative_config=None, tokenizer='/opt/lung/llm/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=32768, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=gptq, enforce_eager=False, kv_cache_dtype=auto, quantization_param_path=None, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='outlines'), observability_config=ObservabilityConfig(otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=0, served_model_name=/opt/lung/llm/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8, num_scheduler_steps=1, chunked_prefill_enabled=False multi_step_stream_outputs=True, enable_prefix_caching=False, use_async_output_proc=True, use_cached_outputs=False, chat_template_text_format=string, mm_processor_kwargs=None, pooler_config=None)\n", "INFO 03-19 13:23:38 selector.py:261] Cannot use FlashAttention-2 backend for Volta and Turing GPUs.\n", "INFO 03-19 13:23:38 selector.py:144] Using XFormers backend.\n", "INFO 03-19 13:23:39 model_runner.py:1072] Starting to load model /opt/lung/llm/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[W319 13:23:39.079105545 CUDAAllocatorConfig.h:28] Warning: expandable_segments not supported on this platform (function operator())\n", "Loading safetensors checkpoint shards: 0% Completed | 0/5 [00:00, ?it/s]\n", "Loading safetensors checkpoint shards: 20% Completed | 1/5 [00:10<00:40, 10.09s/it]\n", "Loading safetensors checkpoint shards: 40% Completed | 2/5 [00:11<00:15, 5.20s/it]\n", "Loading safetensors checkpoint shards: 60% Completed | 3/5 [00:38<00:30, 15.17s/it]\n", "Loading safetensors checkpoint shards: 80% Completed | 4/5 [00:43<00:10, 10.93s/it]\n", "Loading safetensors checkpoint shards: 100% Completed | 5/5 [00:46<00:00, 8.23s/it]\n", "Loading safetensors checkpoint shards: 100% Completed | 5/5 [00:46<00:00, 9.35s/it]\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO 03-19 13:24:27 model_runner.py:1077] Loading model weights took 15.5028 GB\n", "INFO 03-19 13:24:38 worker.py:232] Memory profiling results: total_gpu_memory=31.73GiB initial_memory_usage=15.89GiB peak_torch_memory=19.42GiB memory_usage_post_profile=15.96GiB non_torch_memory=0.45GiB kv_cache_size=8.69GiB gpu_memory_utilization=0.90\n", "INFO 03-19 13:24:38 gpu_executor.py:113] # GPU blocks: 2965, # CPU blocks: 1365\n", "INFO 03-19 13:24:38 gpu_executor.py:117] Maximum concurrency for 32768 tokens per request: 1.45x\n", "INFO 03-19 13:24:42 model_runner.py:1400] Capturing cudagraphs for decoding. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.\n", "INFO 03-19 13:24:42 model_runner.py:1404] If out-of-memory error occurs during cudagraph capture, consider decreasing `gpu_memory_utilization` or switching to eager mode. You can also reduce the `max_num_seqs` as needed to decrease memory usage.\n", "INFO 03-19 13:25:05 model_runner.py:1518] Graph capturing finished in 23 secs, took 0.59 GiB\n" ] } ], "source": [ "import os\n", "import json\n", "# import time\n", "os.environ[\"NCCL_P2P_DISABLE\"] = \"1\"\n", "import torch \n", "# import pynvml\n", "from vllm import LLM, SamplingParams\n", "import torch.distributed as dist\n", "import re\n", "torch.cuda.empty_cache()\n", "os.environ[\"TRANSFORMERS_OFFLINE\"] = \"1\"\n", "os.environ[\"HF_DATASETS_OFFLINE\"] = \"1\"\n", "os.environ[\"PYTORCH_CUDA_ALLOC_CONF\"] = \"expandable_segments:True\"\n", "\n", "\n", "\n", "# 加载量化模型\n", "llm = LLM(model=\"/opt/lung/llm/Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8\", dtype=\"half\",gpu_memory_utilization=0.9)\n", "\n", "# \n", "sampling_params = SamplingParams(temperature=0.1, top_p=0.3, max_tokens = 256)\n", "\n", "# 推理示例\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Id | \n", "PatientName | \n", "IPBLH | \n", "OPBLH | \n", "KH | \n", "KLX | \n", "SexId | \n", "CSRQ | \n", "ZJLX | \n", "SFZH | \n", "... | \n", "ValueString | \n", "DisplayString | \n", "ValuePostfix | \n", "WSJLSCSJ | \n", "WSJLXGSJ | \n", "upload_time | \n", "规范节点名 | \n", "规范注释 | \n", "规范说明 | \n", "processed_string | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "测试 | \n", "测试 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hzxm | \n", "患者姓名 | \n", "NaN | \n", "测试 | \n", "
1 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "女 | \n", "女 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hzxb | \n", "患者性别 | \n", "NaN | \n", "女 | \n", "
2 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "22岁 | \n", "22岁 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hznl | \n", "患者年龄 | \n", "NaN | \n", "22岁 | \n", "
3 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "发生发放安抚啊医院 | \n", "发生发放安抚啊医院 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJL$zs | \n", "主诉 | \n", "NaN | \n", "发生发放安抚啊医院 | \n", "
4 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "6.38528E+17 | \n", "2024年05月31日20时56分 | \n", "收入我科入院。 | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_CYXJ$rysqk_rysj | \n", "入院时情况-入院时间 | \n", "NaN | \n", "2024年05月31日20时56分 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
122 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "Ib | \n", "Ib | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "Ib | \n", "
123 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "右 | \n", "右 | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "右 | \n", "
124 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "Ia | \n", "Ia | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "Ia | \n", "
125 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "NaN | \n", "\n", " | NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$zdys | \n", "主刀医师 | \n", "NaN | \n", "\n", " |
126 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "6.38712E+17 | \n", "2024年12月30日 17时11分 | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$zdys | \n", "主刀医师 | \n", "NaN | \n", "2024年12月30日 17时11分 | \n", "
127 rows × 54 columns
\n", "\n", " | Id | \n", "PatientName | \n", "IPBLH | \n", "OPBLH | \n", "KH | \n", "KLX | \n", "SexId | \n", "CSRQ | \n", "ZJLX | \n", "SFZH | \n", "... | \n", "ValueString | \n", "DisplayString | \n", "ValuePostfix | \n", "WSJLSCSJ | \n", "WSJLXGSJ | \n", "upload_time | \n", "规范节点名 | \n", "规范注释 | \n", "规范说明 | \n", "processed_string | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "测试 | \n", "测试 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hzxm | \n", "患者姓名 | \n", "NaN | \n", "测试 | \n", "
1 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "女 | \n", "女 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hzxb | \n", "患者性别 | \n", "NaN | \n", "女 | \n", "
2 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "22岁 | \n", "22岁 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJLFL$hznl | \n", "患者年龄 | \n", "NaN | \n", "22岁 | \n", "
3 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "发生发放安抚啊医院 | \n", "发生发放安抚啊医院 | \n", "NaN | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_RYJL$zs | \n", "主诉 | \n", "NaN | \n", "发生发放安抚啊医院 | \n", "
4 | \n", "507444 | \n", "林* | \n", "1559494 | \n", "NaN | \n", "9948848999 | \n", "3 | \n", "2 | \n", "2002/10/2 | \n", "1 | \n", "377474********0222 | \n", "... | \n", "6.38528E+17 | \n", "2024年05月31日20时56分 | \n", "收入我科入院。 | \n", "2024/11/28 14:08 | \n", "2024/11/28 14:09 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_CYXJ$rysqk_rysj | \n", "入院时情况-入院时间 | \n", "NaN | \n", "2024年05月31日20时56分 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
122 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "Ib | \n", "Ib | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "Ib | \n", "
123 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "右 | \n", "右 | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "右 | \n", "
124 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "Ia | \n", "Ia | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$ssjg | \n", "手术经过 | \n", "NaN | \n", "Ia | \n", "
125 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "NaN | \n", "\n", " | NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$zdys | \n", "主刀医师 | \n", "NaN | \n", "\n", " |
126 | \n", "1571219 | \n", "张* | \n", "1615739 | \n", "NaN | \n", "167313826_320500 | \n", "4 | \n", "2 | \n", "1994/10/23 | \n", "1 | \n", "350301********2829 | \n", "... | \n", "6.38712E+17 | \n", "2024年12月30日 17时11分 | \n", "NaN | \n", "2024/12/30 17:18 | \n", "2024/12/30 17:23 | \n", "2025/2/8 12:05 | \n", "COC_HBZL_SSJL$zdys | \n", "主刀医师 | \n", "NaN | \n", "2024年12月30日 17时11分 | \n", "
127 rows × 54 columns
\n", "