硬件:Ascend NPU(Ascend 910B4) · 推理引擎:torch_npu · 设备:npu:0 精度验收:CPU vs NPU 推理精度差异 < 1%(实测 PASS,cosine=1.0)
YingLong model is introduced in this paper. This version is pre-trained on 78B time points. More details can be found at our [github](https://github.com
| 属性 | 值 |
|---|---|
| 模型名 | qcw2333/YingLong_110m |
| 原始权重 | ModelScope / HuggingFace / AtomGit 镜像 |
| 任务类型 | time-series-forecasting |
| 输入 | 历史时间序列 [batch, 1, 512](512 步历史) |
| 输出 | 预测序列 [batch, 1, 128](未来 128 步) |
| 框架 | PyTorch + torch_npu |
| 官方实现 | https://github.com/wxie9/YingLong |
官方实现 / 论文仓库:
| 依赖项 | 版本 | 说明 |
|---|---|---|
| Python | 3.12 | conda 环境 qcw2333-yinglong_110m-npu |
| torch / torch_npu | 2.10.0 / 2.10.0 | 由 setup_env.sh 装,须严格配套 |
| transformers | ==5.15.0 | |
| numpy | ==2.5.2 | |
| pandas | ==2.3.3 | |
| huggingface-hub | ==1.27.0 | |
| modelscope | ==1.39.1 | |
| safetensors | ==0.8.0 | |
| pyyaml | >=6.0 | |
| lightning-utilities | ==0.15.0 # remote code 隐式依赖 | |
| einops | ==0.8.0 # model.py rearrange 隐式依赖 |
一键建环境(从零创建 conda 环境并装依赖):
bash setup_env.sh # conda create -n <env> python=<ver> + torch/torch_npu + requirements.txt⚠️ 重要:若环境已装 torch/torch_npu,不要强制覆盖 torch,否则破坏 torch_npu 算子插件绑定。
国内 pip 源(Tsinghua):https://pypi.tuna.tsinghua.edu.cn/simple
权重不随仓库分发,推理前先用国内下载源拉取到本地缓存(推荐 ModelScope,失败回落 HF 镜像):
# 方式一:ModelScope(国内直连,最快)
pip install modelscope -i https://pypi.tuna.tsinghua.edu.cn/simple
python -c "from modelscope import snapshot_download; snapshot_download('qcw2333/YingLong_110m', cache_dir='./weights')"
# 方式二:HF 镜像(hf-mirror.com)
export HF_ENDPOINT=https://hf-mirror.com
huggingface-cli download qcw2333/YingLong_110m --local-dir ./weights/YingLong_110minference.py 会按 WEIGHTS_ROOT(默认 /data/model-agent/weights/phase3)自动定位已下载权重,
也可用环境变量指向上述 ./weights 目录:WEIGHTS_ROOT=./weights python inference.py
硬件:单卡 Ascend 910B4(npu:0,物理卡 4)
评委裸 clone 后本机没有 conda 环境,conda activate 不会创建环境。必须先建环境再推理:
# 第一步:从零创建 conda 环境并装依赖(conda create + torch/torch_npu + requirements.txt)
bash setup_env.sh
# 第二步:激活环境并一键推理(环境自检 + inference + eval + benchmark)
conda activate qcw2333-yinglong_110m-npu
bash run.shimport torch, torch_npu
from ts_adapter import create_adapter, move_to_device
model_name = "qcw2333/YingLong_110m"
adapter = create_adapter(model_name, model_dir) # model_dir 由 WEIGHTS_ROOT 定位
adapter.load(); adapter.to_device('npu:0')
inputs = move_to_device(adapter.generate_input(batch_size=1), 'npu:0')
prediction = adapter.predict(inputs) # [1, channels, pred_len] 预测序列logs/inference.log)输入:示例序列/文本(见 inference.py)
输出:
=== Time-Series Inference: qcw2333/YingLong_110m on Ascend NPU ===
NPU: npu:0(物理卡 7)
family: yinglong | ctx=512 | pred=128 | channels=1
权重目录: /data/model-agent/weights/phase3/qcw2333/YingLong_110m
输入历史序列 shape: (见 adapter)
预测 shape: (1, 128)
推理耗时: 436.35 ms
预测前 8 值: [108.95319366455078, 108.99365234375, 109.22544860839844, 109.55537414550781, 109.51409912109375, 109.13236999511719, 108.77631378173828, 108.60604858398438]
预测 L2 norm: 1136.6760logs/accuracy.log)=== CPU-NPU Accuracy: qcw2333/YingLong_110m (FP32) ===
max_abs_error 0.000038
mean_abs_error 0.000012
relative_error 0.0000%
max_relative_error 0.0000%
cosine_similarity 1.000000
结果 PASS(阈值 max_relative_error < 1.0%)| 指标 | 数值 |
|---|---|
| max_abs_error | 0.000038 |
| relative_error | 0.0000% |
| cosine_similarity | 1.000000 |
注:本次适配无精度要求,精度数据作为质量证据。详见
logs/accuracy.log。
| 指标 | 数值 |
|---|---|
| avg latency | 30.26 ms |
| p50 | 30.53 ms |
| throughput | 33.04 samples/sec |



截图由真实执行日志(
logs/)忠实渲染为终端风格 PNG,渲染脚本tools/gen_screenshots_pw.py(playwright),可复现,无虚构结果。
#NPU #Ascend #Ascend910 #model-agent-tagged
仓库:https://gitcode.com/v_50/qcw2333-YingLong_110m-NPU 适配日期:2026-08-12 | 赛道:第二季·模型适配·阶段三