IBM Research PatchTSMixer forecasting checkpoint for the 7-channel ETTh1 dataset (KDD'23, arXiv:2306.09364), adapted for Ascend NPU via torch_npu.
PatchTSMixer (PatchTST-style time-series
forecasting with MLP-Mixer) segments a time series into patches and mixes
them with a lightweight channel-mixing MLP-Mixer backbone. This checkpoint is
the fine-tuned forecasting model (PatchTSMixerForPrediction) pre-trained
on the ETTh1 training split (7 channels: HUFL/HULL/MUFL/MULL/LUFL/LULL/OT).
Note:
ibm-research/test-patchtsmixeris an IBM Research test/scratch release whoseconfig.jsonandmodel.safetensorsare byte-identical to the officialibm-granite/granite-timeseries-patchtsmixer. It is served here as a standalone time-series-forecasting endpoint.
Architecture: PatchTSMixerForPrediction (native in transformers 4.57.6)
patch_length=16, patch_stride=16 → 32 patchesd_model=48, expansion_factor=3,
gated_attn=truestd scaling (RevIN-style), common_channel mixing mode, sincos positional encodingloss=mse, distribution_output=student_t)vLLM-Ascend 0.18 is not used (PatchTSMixer is a non-autoregressive
time-series model, absent from the 317-architecture LLM registry).
The model runs on torch_npu + transformers 4.57.6 native PatchTSMixerForPrediction
with zero source modifications — PatchTSMixer ships out of the box in
transformers 4.57.6 (no vendoring, no patching). Every operator used
(eager matmul / LayerNorm / GELU / sigmoid / std scaling) is natively
supported by the Ascend NPU.
torch_npu 2.9.0.post1# 1. download weights (GitCode HF-mirror first, ModelScope fallback; sha256-verified)
python download_model.py
# 2. generate demo data
python make_test_data.py
# 3. start the service (npu:1, port 8058)
./start_serve.sh # or: python server.py --port 8058
# 4. test the service
python test_server.py --port 8058
# 5. verify NPU vs CPU numerics
python verify_npu_vs_cpu.pycurl -X POST http://127.0.0.1:8058/v1/forecast \
-H 'Content-Type: application/json' \
-d @demo_series.json
# -> {"prediction": [[[...], ...]], "loc": [...], "scale": [...],
# "prediction_length": 96, "context_length": 512, "latency_ms": 5.0, ...}Request body (past_values) accepts [T], [T, C] or [B, T, C] (float32).
Each series must have length >= 512; the most recent 512 points are used.
Response prediction has shape [B, 96, C] (one forecast per input channel).
| Metric | Value |
|---|---|
| Model load | ~1.1 s |
| Steady-state forward (NPU) | ~1.6–1.8 ms |
| Steady-state HTTP p50 | 5.99 ms / p95 6.06 ms |
| CPU single-core forward | ~3.2 ms |
| NPU vs CPU cosine | 1.0000000000 |
| NPU vs CPU max_abs_diff | 2.20e-04 |
| HBM usage (process) | 126 MB |
| Port / device | 8058 / npu:1 |
inference.py — PatchTSMixerEngine (torch_npu inference, [B,T,C] input)server.py — FastAPI service (/v1/forecast, /health)download_model.py — GitCode HF-mirror + ModelScope downloader (sha256 idempotent)make_test_data.py — ETTh1-style 7-channel synthetic demo dataverify_npu_vs_cpu.py — NPU vs CPU numerical equivalence checktest_server.py — HTTP end-to-end smoke teststart_serve.sh — one-click start scriptassets/ — screenshot materials (workflow / result / npu-smi)Model weights are not committed to this repository; run download_model.py
to fetch them.