cisco-ai/cisco-time-series-model-1.0-previewbf56b7946c42912ddb05dbf14aabc59f0974d31bPatchedTSMultiResolutionDecoder (50 layers, 16 heads, hidden 1280, patch 32, horizon 128, 9 quantiles)Univariate zero-shot forecasting with multiresolution context:
| Field | Value |
|---|---|
| input_shape | [B, T] fine series, T up to 30720 (512*60), will be split into coarse (block mean, 60) and fine (last 512) |
| context_length_fine | 512 |
| context_length_coarse | 512 |
| horizon_length | 128 |
| patch_length | 32 |
| quantiles | [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9] |
| preprocessing | strip_leading_nans, linear_interpolation, block-agg mean, left-pad/truncate to 512, per-series normalize (mean/std) |
| dtype | float32 (model), bfloat32 internally |
| output | mean (128,) + quantiles dict 9x128 |
| scaling | per-series normalize, then denormalize with fine stats + global_eps 1e-8 |
Synthetic example used for validation (official README):
rng = np.random.default_rng(42)
T = 512*60
hours = (T+59)//60
k = np.arange(hours, dtype=np.float32)
h = (80+0.1*k)*(1+0.25*np.sin(2*np.pi*k/24))
t = np.arange(T, dtype=np.float32)
input_series = h[(t//60).astype(int)]*(1+0.05*np.sin(2*np.pi*t/30)) + rng.normal(0,0.4,size=T)
# -> mean 105.80, std 24.23, shape (30720,)assets/npu_device_call.pngtorch.npu.is_available()==True, torch.npu.device_count()==2, npu:0 selectedpip install -r requirements.txt
# requirements.txt includes torch, torch_npu, numpy, pandas, safetensors, huggingface_hub, timesfmpython inference.pyinference.py is self-contained, loads PatchedTSMultiResolutionDecoder with CiscoTsmMR wrapper, forces npu:0, and runs model.forecast with torch.npu.synchronize() before/after timing.
Logs at least: model_name, task, backend, device, dtype, first_param device, input summary, output summary, sync time, final status.
model_name: cisco-ai/cisco-time-series-model-1.0-preview
task: time-series forecasting (multiresolution, horizon=128, quantiles=9)
npu_device: Ascend910_9362
npu:0 selected
input_series: shape (30720,) mean 105.80 std 24.23
checkpoint: local /tmp/cisco_local/torch_model.pt (2.00 GB)
model device: npu:0
first_param device: npu:0, dtype: torch.float32
Warmup (3x)... done
Timed inference (10x)... avg 69.1ms min 69.1ms max 69.2ms
Final forecast mean first 5: [162.87169 164.54495 166.25671 167.41878 168.21675]
mean last 5: [158.44936 159.15125 159.71005 160.08667 160.39111]
quantiles: ['0.1','0.2','0.3','0.4','0.5','0.6','0.7','0.8','0.9']
q=0.1 first 3: [162.21043 163.44492 165.17612]
q=0.5 first 3: [162.88153 164.42165 166.14124]
q=0.9 first 3: [163.63788 165.4454 167.20401]
Multi-series: series0 mean[0]=162.87, series1 mean[0]=79.88
STATUS: PASSFull output in assets/model_result.png.
Second series (25000 length) also verified.
Same weights (torch_model.pt sha256 f29111cf1f0e94660f0b6b1edfb0778d6df36406e536aeff9ec9b01d5679fd31), same input, preprocessing, dtype float32, seed 42, eval mode.
/tmp/cisco_cpu.npy/tmp/cisco_npu.npypython scripts/compare_outputs.py --cpu /tmp/cisco_cpu.npy --npu /tmp/cisco_npu.npy --task regression --atol 1e-4 --rtol 1e-3Result:
{"task":"regression","cpu_shape":[128],"npu_shape":[128],"max_abs_error":7.62939453125e-05,"mean_abs_error":2.372264862060547e-05,"passed":true}Threshold atol=1e-4, rtol=1e-3 for FP32, quantile monotonicity checked, finite values verified. Single-window smoke consistency (not full benchmark) - passed.
No CPU fallback observed; model and tensors explicitly on npu:0.
torch.npu.synchronize() before/afterImages generated via xterm.js from real logs (not screenshots), dark background #282828, prompt atomgit@pod-a94f8701860f4700b161b00e290de466:~$:
assets/agent_workflow.png - workflow: env, download, inspect, NPU load, consistency, benchmark, validateassets/npu_device_call.png - npu-smi, torch.npu, device, param device, input/output deviceassets/model_result.png - default python inference.py full outputReference in README only, no disclosure of render tool details beyond "xterm.js".
npu-smi info && python scripts/check_npu.pypython inference.py (auto-downloads weights if missing via huggingface_hub)python scripts/compare_outputs.py --cpu cpu.npy --npu npu.npy --task regression