[AINode]: Integrate MOMENT as a builtin forecasting model

[Eliaaazzz]

Description

Integrate MOMENT Time Series Foundation Model

Integrate MOMENT (A Family of Open Time-series Foundation Models, ICML 2024, Auton Lab/CMU) into IoTDB AINode as a built-in forecasting model.

MOMENT uses a T5 encoder-only backbone with patch-based input embedding and RevIN (Reversible Instance Normalization). It supports zero-shot forecasting with a fixed input length of 512 timesteps
and channel-independent multivariate processing.

Architecture:
Input [batch, n_channels, 512]
→ RevIN normalization
→ Patching (patch_len=8, stride=8 → 64 patches)
→ Patch embedding (linear → d_model)
→ T5 Encoder (self-attention)
→ ForecastingHead (linear → forecast_horizon)
→ RevIN denormalization
→ Output [batch, n_channels, forecast_horizon]

The default variant is MOMENT-1-small (~152 MB, d_model=512, 6 layers). Weights are downloaded from HuggingFace Hub on first use, consistent with existing built-in models (Sundial, Timer-XL,
Chronos2, etc.).

Design Decisions

• Vendor the model code rather than depending on the external momentfm pip package, following the same pattern as Chronos2 ([AINode] Integrate Chronos2 as builtin forecasting model #16903) and Toto ([AINode]: Integrate toto as a builtin forecasting model #17322). This avoids an additional runtime
  dependency and gives full control over the loading process.
• Wrap as PreTrainedModel with custom from_pretrained() to handle upstream MOMENT's flat state-dict key mapping (prefixing with moment.*) and T5 config extraction from config.json.
• Use MOMENT-1-small as the default built-in variant to minimize download size and memory usage while still providing useful forecasting capability.
• Iterative long-horizon forecasting in the pipeline: for output_length > model_forecast_horizon, predictions are appended to the context window and fed back as input, similar to
  autoregressive decoding.
• Fixed 512-length input handling: inputs shorter than 512 are left-padded with zeros and masked; inputs longer than 512 are truncated to the last 512 timesteps.

Bug Fix

Fixed unquoted $JAVA variable in confignode-env.sh and datanode-env.sh to handle paths with spaces (e.g. C:\Program Files\...).

---

This PR has:

• been self-reviewed.
• added or updated version, license, or notice information
• added comments explaining the "why" and the intent of the code wherever would not be obvious for an unfamiliar reader.
• added integration tests.
• been tested in a test IoTDB cluster.

---

Key changed/added classes (or packages if there are too many classes) in this PR

• iotdb-core/ainode/iotdb/ainode/core/model/moment/ — New MOMENT model package
  • configuration_moment.py — MomentConfig(PretrainedConfig)
  • modeling_moment.py — MomentForPrediction(PreTrainedModel) with RevIN, Patching, T5 Encoder, ForecastingHead
  • pipeline_moment.py — MomentPipeline(ForecastPipeline) with padding/truncation and iterative forecasting
• iotdb-core/ainode/iotdb/ainode/core/model/model_info.py — Added moment to BUILTIN_HF_TRANSFORMERS_MODEL_MAP
• iotdb-core/ainode/iotdb/ainode/core/constant.py — Added memory estimate for MOMENT
• integration-test/.../AINodeTestUtils.java — Added moment to BUILTIN_LTSM_MAP
• LICENSE — Added MIT attribution for MOMENT source code
• scripts/conf/confignode-env.sh, scripts/conf/datanode-env.sh — Fixed unquoted $JAVA variable

[CRZbulabula]

Hi Elia, this is your first PR (pull request) for Apache IoTDB repository, our community highly appreciate your contribution!

Next, let us talk about this PR, the following points still need to be improved:

1. The moment model has serveral versions, we can employ the large version.
2. The format of AINode should be fixed. Run black . && isort . under iotdb-core/ainode.
3. The forecast IT failed, you should ensure the correctness first in your local environment.
4. The modification in constant.py should be reverted, since we do not support the corresponding function in current version.

[Eliaaazzz]

Hi Elia, this is your first PR (pull request) for Apache IoTDB repository, our community highly appreciate your contribution!

Next, let us talk about this PR, the following points still need to be improved:

1. The moment model has serveral versions, we can employ the large version.
2. The format of AINode should be fixed. Run black . && isort . under iotdb-core/ainode.
3. The forecast IT failed, you should ensure the correctness first in your local environment.
4. The modification in constant.py should be reverted, since we do not support the corresponding function in current version.

Thanks for the review and warm welcome. I will fix these in the next update.

• I will use the larger model version when multiple versions are available.
• I will run black . && isort . under iotdb-core/ainode and fix the AINode formatting issues.
• I will reproduce the forecast integration test failure locally and make sure it passes before pushing the next revision.
• I will revert the change in constant.py, since that function is not supported in the current version.

[Eliaaazzz]

I‘m still trying to reproduce the forecast IT errors and I'll push a new commit right after I fixed the errors. Please bear with me.