This is an automated email from the ASF dual-hosted git repository.
CritasWang pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iotdb-docs.git
The following commit(s) were added to refs/heads/main by this push:
new 6934feb2 docs: remove Moirai2 model documentation (#1191)
6934feb2 is described below
commit 6934feb2c9da044a308baef6411c75e78fb1d1de
Author: leto-bbq <[email protected]>
AuthorDate: Thu Jul 30 16:05:20 2026 +0800
docs: remove Moirai2 model documentation (#1191)
---
.../Table/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../Tree/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../latest/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../Table/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../Tree/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
.../latest/AI-capability/AINode_Upgrade_apache.md | 2 --
.../TimeSeries-Large-Model_Upgrade_apache.md | 24 +++-------------------
16 files changed, 24 insertions(+), 184 deletions(-)
diff --git a/src/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
b/src/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
index fc7d3625..9cb5f68b 100644
--- a/src/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
+++ b/src/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
@@ -436,7 +436,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -461,7 +460,6 @@ IoTDB> show models
| **Timer-XL** | Long-context time series large model pretrained on massive
industrial data | Complex industrial forecasting requiring ultra-long history
(energy, aerospace, transport) | 1. Supports input of tens of thousands of time
points<br>2. Covers non-stationary, multivariate, and covariate scenarios<br>3.
Pretrained on trillion-scale high-quality industrial IoT data |
| **Timer-Sundial** | Generative foundation model with "Transformer +
TimeFlow" architecture | Zero-shot forecasting requiring uncertainty
quantification (finance, supply chain, renewable energy) | 1. Strong zero-shot
generalization; supports point & probabilistic forecasting<br>2. Flexible
analysis of any prediction distribution statistic<br>3. Innovative
flow-matching architecture for efficient non-deterministic sample generation |
| **Chronos-2** | Universal time series foundation model based on discrete
tokenization | Rapid zero-shot univariate forecasting; scenarios enhanced
by covariates (promotions, weather) | 1. Powerful zero-shot probabilistic
forecasting<br>2. Unified multi-variable & covariate modeling (strict input
requirements):<br> a. Future covariate names ⊆ historical covariate
names<br> b. Each historical covariate length = target
length<br> c. Each future cov [...]
-| **Moirai 2.0** | Lightweight decoder-only Patch Transformer with a single
patch size, multi-token prediction, and multi-quantile outputs | Zero-shot
univariate forecasting where model size and inference efficiency are important,
such as industrial monitoring, energy load, and equipment metrics | 1.
Approximately 11.4M parameters<br>2. Predicts multiple patches per decoding
step to reduce autoregressive overhead for long horizons<br>3. Outputs nine
quantiles (0.1–0.9) and uses the p50 m [...]
| **Toto 2.0** | Decoder-only Patch Transformer alternating causal temporal
attention and variable attention to jointly model temporal and variable
dimensions | Zero-shot multivariate forecasting for observability metrics,
including joint forecasting of CPU, memory, and network traffic | 1. Supports
univariate and multivariate target forecasting<br>2. Outputs fixed quantiles
from 0.1 to 0.9 and uses the p50 median as the point forecast<br>3. Supports
cached block decoding for efficient s [...]
### 4.4 Deleting Models
diff --git
a/src/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 284198ab..760052da 100644
---
a/src/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2<sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]<
-## 7. Moirai2 Model
+## 7. Toto Model
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Moirai 2.0) is a general-purpose time series foundation
model developed by Salesforce AI Research (supported in V2.0.10 and later).
AINode currently integrates the Moirai 2.0 R-small variant, which has
approximately 11.4M parameters. Unlike Moirai 1.0, which uses a masked encoder
architecture, Moirai 2.0 uses a causal decoder-only Patch Transformer. With a
single patch size, multi-token prediction, a [...]
-
-- **Lightweight Model Architecture**: Uses a decoder-only Patch Transformer
with RMSNorm, rotary positional embeddings, and SiLU-GLU feed-forward networks
to balance forecasting capability and inference efficiency at a small parameter
scale.
-- **Multi-Token Prediction**: Predicts multiple patches at each decoding step,
reducing the number of autoregressive decoding steps required for long forecast
horizons.
-- **Probabilistic Forecasting**: Outputs nine quantiles from 0.1 to 0.9.
AINode uses the p50 median as the point forecast.
-- **Patch Decoding**: Groups the time series into fixed-size patches before
the attention module to improve temporal feature extraction and decoding
efficiency.
-- **Instance Normalization**: Standardizes each time series before model input
and applies denormalization after output to mitigate distribution shifts across
series.
-- **Input Scope**: Focuses on univariate forecasting and does not support
multivariate targets or covariates.
-
-
-
-> Note: The Moirai 2.0 R-small model weights are licensed under CC BY-NC 4.0
and are restricted to research use.
-
-## 8. Toto Model
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
- **Univariate and Multivariate Forecasting**: Supports both individual target
variables and joint forecasting of multiple related target variables, making it
suitable for observability metrics such as CPU, memory, and network traffic.
- **Probabilistic Forecasting**: Outputs fixed quantiles from 0.1 to 0.9 to
represent forecasting uncertainty. AINode uses the p50 median as the point
forecast.
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821**. [↩ Back](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ Back](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref5)
diff --git a/src/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
b/src/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
index 0f614b41..be7243e6 100644
--- a/src/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
+++ b/src/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
@@ -420,7 +420,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -445,7 +444,6 @@ Built-in time series large model introduction:
| **Timer-XL** | Time series large model supporting ultra-long context,
enhancing generalization capability through large-scale industrial data
pre-training. | Complex industrial prediction requiring extremely long
historical data, such as energy, aerospace, and transportation. | 1.
Ultra-long context support, can handle tens of thousands of time points as
input. <br>2. Multi-scenario coverage, supports non-stationary, multi-variable,
and covariate prediction. <br>3. Pre-trained [...]
| **Timer-Sundial** | A generative foundational model based on "Transformer +
TimeFlow" architecture, focusing on probabilistic prediction. | Zero-shot
prediction scenarios requiring quantification of uncertainty, such as finance,
supply chain, and new energy power generation. | 1. Strong zero-shot
generalization capability, supports point prediction and probabilistic
prediction. <br>2. Can flexibly analyze any statistical properties of the
prediction distribution. <br>3. Innovative [...]
| **Chronos-2** | A general time series foundational model based on discrete
tokenization paradigm, converting prediction into language modeling tasks.
| Rapid zero-shot univariate prediction, and scenarios that can leverage
covariates (e.g., promotions, weather) to improve results. | 1. Strong
zero-shot probabilistic prediction capability. <br>2. Supports unified
covariate modeling, but has strict input requirements:<br> a. The
set of names of future covariates must be a [...]
-| **Moirai 2.0** | Uses a lightweight decoder-only Patch Transformer with a
single patch size, multi-token prediction, and multi-quantile outputs for
efficient univariate forecasting. | Zero-shot univariate forecasting where
model size and inference efficiency are important, such as industrial
monitoring, energy load, and equipment metric forecasting. | 1. Approximately
11.4M parameters.<br>2. Predicts multiple patches per decoding step to reduce
autoregressive overhead for long horizons [...]
| **Toto 2.0** | Uses a decoder-only Patch Transformer that alternates causal
temporal attention and variable attention to jointly model the temporal and
variable dimensions. | Zero-shot forecasting for multivariate time series such
as observability metrics, including joint forecasting of CPU, memory, and
network traffic. | 1. Supports univariate and multivariate target
forecasting.<br>2. Outputs fixed quantiles from 0.1 to 0.9 and uses the p50
median as the point forecast.<br>3. Support [...]
### 4.4 Delete Models
diff --git
a/src/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 284198ab..760052da 100644
---
a/src/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2<sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]<
-## 7. Moirai2 Model
+## 7. Toto Model
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Moirai 2.0) is a general-purpose time series foundation
model developed by Salesforce AI Research (supported in V2.0.10 and later).
AINode currently integrates the Moirai 2.0 R-small variant, which has
approximately 11.4M parameters. Unlike Moirai 1.0, which uses a masked encoder
architecture, Moirai 2.0 uses a causal decoder-only Patch Transformer. With a
single patch size, multi-token prediction, a [...]
-
-- **Lightweight Model Architecture**: Uses a decoder-only Patch Transformer
with RMSNorm, rotary positional embeddings, and SiLU-GLU feed-forward networks
to balance forecasting capability and inference efficiency at a small parameter
scale.
-- **Multi-Token Prediction**: Predicts multiple patches at each decoding step,
reducing the number of autoregressive decoding steps required for long forecast
horizons.
-- **Probabilistic Forecasting**: Outputs nine quantiles from 0.1 to 0.9.
AINode uses the p50 median as the point forecast.
-- **Patch Decoding**: Groups the time series into fixed-size patches before
the attention module to improve temporal feature extraction and decoding
efficiency.
-- **Instance Normalization**: Standardizes each time series before model input
and applies denormalization after output to mitigate distribution shifts across
series.
-- **Input Scope**: Focuses on univariate forecasting and does not support
multivariate targets or covariates.
-
-
-
-> Note: The Moirai 2.0 R-small model weights are licensed under CC BY-NC 4.0
and are restricted to research use.
-
-## 8. Toto Model
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
- **Univariate and Multivariate Forecasting**: Supports both individual target
variables and joint forecasting of multiple related target variables, making it
suitable for observability metrics such as CPU, memory, and network traffic.
- **Probabilistic Forecasting**: Outputs fixed quantiles from 0.1 to 0.9 to
represent forecasting uncertainty. AINode uses the p50 median as the point
forecast.
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821**. [↩ Back](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ Back](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref5)
diff --git a/src/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
b/src/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
index fc7d3625..9cb5f68b 100644
--- a/src/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
+++ b/src/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
@@ -436,7 +436,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -461,7 +460,6 @@ IoTDB> show models
| **Timer-XL** | Long-context time series large model pretrained on massive
industrial data | Complex industrial forecasting requiring ultra-long history
(energy, aerospace, transport) | 1. Supports input of tens of thousands of time
points<br>2. Covers non-stationary, multivariate, and covariate scenarios<br>3.
Pretrained on trillion-scale high-quality industrial IoT data |
| **Timer-Sundial** | Generative foundation model with "Transformer +
TimeFlow" architecture | Zero-shot forecasting requiring uncertainty
quantification (finance, supply chain, renewable energy) | 1. Strong zero-shot
generalization; supports point & probabilistic forecasting<br>2. Flexible
analysis of any prediction distribution statistic<br>3. Innovative
flow-matching architecture for efficient non-deterministic sample generation |
| **Chronos-2** | Universal time series foundation model based on discrete
tokenization | Rapid zero-shot univariate forecasting; scenarios enhanced
by covariates (promotions, weather) | 1. Powerful zero-shot probabilistic
forecasting<br>2. Unified multi-variable & covariate modeling (strict input
requirements):<br> a. Future covariate names ⊆ historical covariate
names<br> b. Each historical covariate length = target
length<br> c. Each future cov [...]
-| **Moirai 2.0** | Lightweight decoder-only Patch Transformer with a single
patch size, multi-token prediction, and multi-quantile outputs | Zero-shot
univariate forecasting where model size and inference efficiency are important,
such as industrial monitoring, energy load, and equipment metrics | 1.
Approximately 11.4M parameters<br>2. Predicts multiple patches per decoding
step to reduce autoregressive overhead for long horizons<br>3. Outputs nine
quantiles (0.1–0.9) and uses the p50 m [...]
| **Toto 2.0** | Decoder-only Patch Transformer alternating causal temporal
attention and variable attention to jointly model temporal and variable
dimensions | Zero-shot multivariate forecasting for observability metrics,
including joint forecasting of CPU, memory, and network traffic | 1. Supports
univariate and multivariate target forecasting<br>2. Outputs fixed quantiles
from 0.1 to 0.9 and uses the p50 median as the point forecast<br>3. Supports
cached block decoding for efficient s [...]
### 4.4 Deleting Models
diff --git
a/src/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 284198ab..760052da 100644
---
a/src/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2<sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]<
-## 7. Moirai2 Model
+## 7. Toto Model
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Moirai 2.0) is a general-purpose time series foundation
model developed by Salesforce AI Research (supported in V2.0.10 and later).
AINode currently integrates the Moirai 2.0 R-small variant, which has
approximately 11.4M parameters. Unlike Moirai 1.0, which uses a masked encoder
architecture, Moirai 2.0 uses a causal decoder-only Patch Transformer. With a
single patch size, multi-token prediction, a [...]
-
-- **Lightweight Model Architecture**: Uses a decoder-only Patch Transformer
with RMSNorm, rotary positional embeddings, and SiLU-GLU feed-forward networks
to balance forecasting capability and inference efficiency at a small parameter
scale.
-- **Multi-Token Prediction**: Predicts multiple patches at each decoding step,
reducing the number of autoregressive decoding steps required for long forecast
horizons.
-- **Probabilistic Forecasting**: Outputs nine quantiles from 0.1 to 0.9.
AINode uses the p50 median as the point forecast.
-- **Patch Decoding**: Groups the time series into fixed-size patches before
the attention module to improve temporal feature extraction and decoding
efficiency.
-- **Instance Normalization**: Standardizes each time series before model input
and applies denormalization after output to mitigate distribution shifts across
series.
-- **Input Scope**: Focuses on univariate forecasting and does not support
multivariate targets or covariates.
-
-
-
-> Note: The Moirai 2.0 R-small model weights are licensed under CC BY-NC 4.0
and are restricted to research use.
-
-## 8. Toto Model
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
- **Univariate and Multivariate Forecasting**: Supports both individual target
variables and joint forecasting of multiple related target variables, making it
suitable for observability metrics such as CPU, memory, and network traffic.
- **Probabilistic Forecasting**: Outputs fixed quantiles from 0.1 to 0.9 to
represent forecasting uncertainty. AINode uses the p50 median as the point
forecast.
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821**. [↩ Back](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ Back](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref5)
diff --git a/src/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
b/src/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
index 0f614b41..be7243e6 100644
--- a/src/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
+++ b/src/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
@@ -420,7 +420,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -445,7 +444,6 @@ Built-in time series large model introduction:
| **Timer-XL** | Time series large model supporting ultra-long context,
enhancing generalization capability through large-scale industrial data
pre-training. | Complex industrial prediction requiring extremely long
historical data, such as energy, aerospace, and transportation. | 1.
Ultra-long context support, can handle tens of thousands of time points as
input. <br>2. Multi-scenario coverage, supports non-stationary, multi-variable,
and covariate prediction. <br>3. Pre-trained [...]
| **Timer-Sundial** | A generative foundational model based on "Transformer +
TimeFlow" architecture, focusing on probabilistic prediction. | Zero-shot
prediction scenarios requiring quantification of uncertainty, such as finance,
supply chain, and new energy power generation. | 1. Strong zero-shot
generalization capability, supports point prediction and probabilistic
prediction. <br>2. Can flexibly analyze any statistical properties of the
prediction distribution. <br>3. Innovative [...]
| **Chronos-2** | A general time series foundational model based on discrete
tokenization paradigm, converting prediction into language modeling tasks.
| Rapid zero-shot univariate prediction, and scenarios that can leverage
covariates (e.g., promotions, weather) to improve results. | 1. Strong
zero-shot probabilistic prediction capability. <br>2. Supports unified
covariate modeling, but has strict input requirements:<br> a. The
set of names of future covariates must be a [...]
-| **Moirai 2.0** | Uses a lightweight decoder-only Patch Transformer with a
single patch size, multi-token prediction, and multi-quantile outputs for
efficient univariate forecasting. | Zero-shot univariate forecasting where
model size and inference efficiency are important, such as industrial
monitoring, energy load, and equipment metric forecasting. | 1. Approximately
11.4M parameters.<br>2. Predicts multiple patches per decoding step to reduce
autoregressive overhead for long horizons [...]
| **Toto 2.0** | Uses a decoder-only Patch Transformer that alternates causal
temporal attention and variable attention to jointly model the temporal and
variable dimensions. | Zero-shot forecasting for multivariate time series such
as observability metrics, including joint forecasting of CPU, memory, and
network traffic. | 1. Supports univariate and multivariate target
forecasting.<br>2. Outputs fixed quantiles from 0.1 to 0.9 and uses the p50
median as the point forecast.<br>3. Support [...]
### 4.4 Delete Models
diff --git
a/src/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 284198ab..760052da 100644
---
a/src/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2<sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]<
-## 7. Moirai2 Model
+## 7. Toto Model
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Moirai 2.0) is a general-purpose time series foundation
model developed by Salesforce AI Research (supported in V2.0.10 and later).
AINode currently integrates the Moirai 2.0 R-small variant, which has
approximately 11.4M parameters. Unlike Moirai 1.0, which uses a masked encoder
architecture, Moirai 2.0 uses a causal decoder-only Patch Transformer. With a
single patch size, multi-token prediction, a [...]
-
-- **Lightweight Model Architecture**: Uses a decoder-only Patch Transformer
with RMSNorm, rotary positional embeddings, and SiLU-GLU feed-forward networks
to balance forecasting capability and inference efficiency at a small parameter
scale.
-- **Multi-Token Prediction**: Predicts multiple patches at each decoding step,
reducing the number of autoregressive decoding steps required for long forecast
horizons.
-- **Probabilistic Forecasting**: Outputs nine quantiles from 0.1 to 0.9.
AINode uses the p50 median as the point forecast.
-- **Patch Decoding**: Groups the time series into fixed-size patches before
the attention module to improve temporal feature extraction and decoding
efficiency.
-- **Instance Normalization**: Standardizes each time series before model input
and applies denormalization after output to mitigate distribution shifts across
series.
-- **Input Scope**: Focuses on univariate forecasting and does not support
multivariate targets or covariates.
-
-
-
-> Note: The Moirai 2.0 R-small model weights are licensed under CC BY-NC 4.0
and are restricted to research use.
-
-## 8. Toto Model
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup> (Toto 2.0) is a next-generation time series foundation
model developed by Datadog (supported in V2.0.10 and later), primarily for
forecasting in observability scenarios. AINode currently integrates the
2.5B-parameter variant. It is based on a decoder-only Patch Transformer
architecture that alternates causal temporal attention and variable attention
to jointly model the temporal and variable dimensions. [...]
- **Univariate and Multivariate Forecasting**: Supports both individual target
variables and joint forecasting of multiple related target variables, making it
suitable for observability metrics such as CPU, memory, and network traffic.
- **Probabilistic Forecasting**: Outputs fixed quantiles from 0.1 to 0.9 to
represent forecasting uncertainty. AINode uses the p50 median as the point
forecast.
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821**. [↩ Back](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ Back](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ Back](#ref5)
diff --git
a/src/zh/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
b/src/zh/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
index 915ef869..9ed5e344 100644
--- a/src/zh/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
+++ b/src/zh/UserGuide/Master/Table/AI-capability/AINode_Upgrade_apache.md
@@ -447,7 +447,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -472,7 +471,6 @@ IoTDB> show models
| **Timer-XL** | 支持超长上下文的时序大模型，通过大规模工业数据预训练增强泛化能力。 |
需利用极长历史数据的复杂工业预测，如能源、航空航天、交通等领域。 | 1. 超长上下文支持，可处理数万时间点输入。<br>2.
多场景覆盖，支持非平稳、多变量及协变量预测。<br>3. 基于万亿级高质量工业时序数据预训练。
|
| **Timer-Sundial** | 采用“Transformer + TimeFlow”架构的生成式基础模型，专注于概率预测。 |
需要量化不确定性的零样本预测场景，如金融、供应链、新能源发电预测。 | 1. 强大的零样本泛化能力，支持点预测与概率预测 <br>2.
可灵活分析预测分布的任意统计特性。<br>3. 创新生成架构，实现高效的非确定性样本生成。
|
| **Chronos-2** | 基于离散词元化范式的通用时序基础模型，将预测转化为语言建模任务。 |
快速零样本单变量预测，以及可借助协变量（如促销、天气）提升效果的场景。 | 1. 强大的零样本概率预测能力。<br>2.
支持协变量统一建模，但对输入有严格要求：<br> a.
未来协变量的名称组成的集合必须是历史协变量的名称组成的集合的子集；<br> b.
每个历史协变量的长度必须等于目标变量的长度；<br> c. 每个未来协变量的长度必须等于预测长度；<br>3.
采用高效的编码器式结构，兼顾性能与推理速度。 |
-| **Moirai 2.0** | 采用轻量级 Decoder-only Patch Transformer，通过单一 Patch 尺寸、多 Token
预测和多分位数输出实现高效的单变量预测。 | 适用于对模型体量和推理效率要求较高的零样本单变量预测，如工业监测、能源负荷及设备指标预测。 | 1.
模型参数量约 11.4M。<br>2. 每个解码步可预测多个 Patch，降低长预测范围的自回归开销。<br>3. 输出 9 个分位数（0.1～0.9），使用
p50 中位数作为点预测。<br>4. 使用实例归一化缓解序列分布漂移。<br>5. 不支持多变量和协变量。 |
| **Toto 2.0** | 采用 Decoder-only Patch
Transformer，交替使用因果时间注意力与变量注意力，对时间维和变量维进行联合建模。 | 面向可观测性指标等多变量时间序列的零样本预测，如
CPU、内存、网络流量等指标的联合预测。 | 1. 支持单变量和多变量目标预测。<br>2. 输出 0.1～0.9 的固定分位数，使用 p50
中位数作为点预测。<br>3. 支持缓存式块解码，可高效扩展较长预测范围。<br>4. 当前不支持协变量。 |
### 4.4 删除模型
diff --git
a/src/zh/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/zh/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 5fe5c377..537acb5b 100644
---
a/src/zh/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/zh/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2 <sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]
-## 7. Moirai2 模型
+## 7. Toto 模型
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Moirai 2.0）是由 Salesforce AI Research 推出的通用时间序列基础模型（V2.0.10
及以后版本支持）。当前集成的是 Moirai 2.0 R-small 版本，模型参数量约为 11.4M。与采用掩码编码器架构的 Moirai 1.0
不同，Moirai 2.0 使用因果 Decoder-only Patch Transformer，并通过单一 Patch 尺寸、多 Token
预测和多分位数输出，在较小模型规模下实现高效的单变量预测。其核心特性包括：
-
-- **轻量化模型架构**：采用 Decoder-only Patch Transformer，并结合 RMSNorm、旋转位置编码和 SiLU-GLU
前馈网络，在较小参数规模下兼顾预测能力和推理效率。
-- **多 Token 预测**：每个解码步骤可同时预测多个 Patch，减少长预测范围下所需的自回归解码次数。
-- **概率性预测能力**：模型输出 0.1～0.9 共 9 个分位数，AINode 使用 p50 中位数作为点预测结果。
-- **Patch 解码**：在进入注意力模块前，将时间序列按照固定大小的 Patch 进行分组，以提高时序特征提取和解码效率。
-- **实例归一化**：在模型输入前对每条时间序列进行标准化，并在输出后执行反归一化，以缓解不同序列间的分布漂移。
-- **输入范围**：模型聚焦于单变量预测，不支持多变量目标及协变量输入。
-
-
-
-> 注意：Moirai 2.0 R-small 模型权重采用 CC BY-NC 4.0 许可证，仅限研究用途。
-
-## 8. Toto 模型
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
- **单变量与多变量预测**：支持单个目标变量以及多个相关目标变量的联合预测，适用于 CPU、内存、网络流量等可观测性指标的分析场景。
- **概率性预测能力**：模型输出 0.1～0.9 的固定分位数，可刻画预测结果的不确定性；AINode 使用 p50 中位数作为点预测结果。
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821.** [↩ 返回](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ 返回](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref5)
diff --git
a/src/zh/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
b/src/zh/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
index 255eaff8..b580ca81 100644
--- a/src/zh/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
+++ b/src/zh/UserGuide/Master/Tree/AI-capability/AINode_Upgrade_apache.md
@@ -423,7 +423,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -448,7 +447,6 @@ IoTDB> show models
| **Timer-XL** | 支持超长上下文的时序大模型，通过大规模工业数据预训练增强泛化能力。 |
需利用极长历史数据的复杂工业预测，如能源、航空航天、交通等领域。 | 1. 超长上下文支持，可处理数万时间点输入。<br>2.
多场景覆盖，支持非平稳、多变量及协变量预测。<br>3. 基于万亿级高质量工业时序数据预训练。
|
| **Timer-Sundial** | 采用“Transformer + TimeFlow”架构的生成式基础模型，专注于概率预测。 |
需要量化不确定性的零样本预测场景，如金融、供应链、新能源发电预测。 | 1. 强大的零样本泛化能力，支持点预测与概率预测 <br>2.
可灵活分析预测分布的任意统计特性。<br>3. 创新生成架构，实现高效的非确定性样本生成。
|
| **Chronos-2** | 基于离散词元化范式的通用时序基础模型，将预测转化为语言建模任务。 |
快速零样本单变量预测，以及可借助协变量（如促销、天气）提升效果的场景。 | 1. 强大的零样本概率预测能力。<br>2.
支持协变量统一建模，但对输入有严格要求：<br> a.
未来协变量的名称组成的集合必须是历史协变量的名称组成的集合的子集；<br> b.
每个历史协变量的长度必须等于目标变量的长度；<br> c. 每个未来协变量的长度必须等于预测长度；<br>3.
采用高效的编码器式结构，兼顾性能与推理速度。 |
-| **Moirai 2.0** | 采用轻量级 Decoder-only Patch Transformer，通过单一 Patch 尺寸、多 Token
预测和多分位数输出实现高效的单变量预测。 | 适用于对模型体量和推理效率要求较高的零样本单变量预测，如工业监测、能源负荷及设备指标预测。 | 1.
模型参数量约 11.4M。<br>2. 每个解码步可预测多个 Patch，降低长预测范围的自回归开销。<br>3. 输出 9 个分位数（0.1～0.9），使用
p50 中位数作为点预测。<br>4. 使用实例归一化缓解序列分布漂移。<br>5. 不支持多变量和协变量。 |
| **Toto 2.0** | 采用 Decoder-only Patch
Transformer，交替使用因果时间注意力与变量注意力，对时间维和变量维进行联合建模。 | 面向可观测性指标等多变量时间序列的零样本预测，如
CPU、内存、网络流量等指标的联合预测。 | 1. 支持单变量和多变量目标预测。<br>2. 输出 0.1～0.9 的固定分位数，使用 p50
中位数作为点预测。<br>3. 支持缓存式块解码，可高效扩展较长预测范围。<br>4. 当前不支持协变量。 |
### 4.4 删除模型
diff --git
a/src/zh/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/zh/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 5fe5c377..537acb5b 100644
---
a/src/zh/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/zh/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2 <sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]
-## 7. Moirai2 模型
+## 7. Toto 模型
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Moirai 2.0）是由 Salesforce AI Research 推出的通用时间序列基础模型（V2.0.10
及以后版本支持）。当前集成的是 Moirai 2.0 R-small 版本，模型参数量约为 11.4M。与采用掩码编码器架构的 Moirai 1.0
不同，Moirai 2.0 使用因果 Decoder-only Patch Transformer，并通过单一 Patch 尺寸、多 Token
预测和多分位数输出，在较小模型规模下实现高效的单变量预测。其核心特性包括：
-
-- **轻量化模型架构**：采用 Decoder-only Patch Transformer，并结合 RMSNorm、旋转位置编码和 SiLU-GLU
前馈网络，在较小参数规模下兼顾预测能力和推理效率。
-- **多 Token 预测**：每个解码步骤可同时预测多个 Patch，减少长预测范围下所需的自回归解码次数。
-- **概率性预测能力**：模型输出 0.1～0.9 共 9 个分位数，AINode 使用 p50 中位数作为点预测结果。
-- **Patch 解码**：在进入注意力模块前，将时间序列按照固定大小的 Patch 进行分组，以提高时序特征提取和解码效率。
-- **实例归一化**：在模型输入前对每条时间序列进行标准化，并在输出后执行反归一化，以缓解不同序列间的分布漂移。
-- **输入范围**：模型聚焦于单变量预测，不支持多变量目标及协变量输入。
-
-
-
-> 注意：Moirai 2.0 R-small 模型权重采用 CC BY-NC 4.0 许可证，仅限研究用途。
-
-## 8. Toto 模型
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
- **单变量与多变量预测**：支持单个目标变量以及多个相关目标变量的联合预测，适用于 CPU、内存、网络流量等可观测性指标的分析场景。
- **概率性预测能力**：模型输出 0.1～0.9 的固定分位数，可刻画预测结果的不确定性；AINode 使用 p50 中位数作为点预测结果。
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821.** [↩ 返回](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ 返回](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref5)
diff --git
a/src/zh/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
b/src/zh/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
index 915ef869..9ed5e344 100644
--- a/src/zh/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
+++ b/src/zh/UserGuide/latest-Table/AI-capability/AINode_Upgrade_apache.md
@@ -447,7 +447,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -472,7 +471,6 @@ IoTDB> show models
| **Timer-XL** | 支持超长上下文的时序大模型，通过大规模工业数据预训练增强泛化能力。 |
需利用极长历史数据的复杂工业预测，如能源、航空航天、交通等领域。 | 1. 超长上下文支持，可处理数万时间点输入。<br>2.
多场景覆盖，支持非平稳、多变量及协变量预测。<br>3. 基于万亿级高质量工业时序数据预训练。
|
| **Timer-Sundial** | 采用“Transformer + TimeFlow”架构的生成式基础模型，专注于概率预测。 |
需要量化不确定性的零样本预测场景，如金融、供应链、新能源发电预测。 | 1. 强大的零样本泛化能力，支持点预测与概率预测 <br>2.
可灵活分析预测分布的任意统计特性。<br>3. 创新生成架构，实现高效的非确定性样本生成。
|
| **Chronos-2** | 基于离散词元化范式的通用时序基础模型，将预测转化为语言建模任务。 |
快速零样本单变量预测，以及可借助协变量（如促销、天气）提升效果的场景。 | 1. 强大的零样本概率预测能力。<br>2.
支持协变量统一建模，但对输入有严格要求：<br> a.
未来协变量的名称组成的集合必须是历史协变量的名称组成的集合的子集；<br> b.
每个历史协变量的长度必须等于目标变量的长度；<br> c. 每个未来协变量的长度必须等于预测长度；<br>3.
采用高效的编码器式结构，兼顾性能与推理速度。 |
-| **Moirai 2.0** | 采用轻量级 Decoder-only Patch Transformer，通过单一 Patch 尺寸、多 Token
预测和多分位数输出实现高效的单变量预测。 | 适用于对模型体量和推理效率要求较高的零样本单变量预测，如工业监测、能源负荷及设备指标预测。 | 1.
模型参数量约 11.4M。<br>2. 每个解码步可预测多个 Patch，降低长预测范围的自回归开销。<br>3. 输出 9 个分位数（0.1～0.9），使用
p50 中位数作为点预测。<br>4. 使用实例归一化缓解序列分布漂移。<br>5. 不支持多变量和协变量。 |
| **Toto 2.0** | 采用 Decoder-only Patch
Transformer，交替使用因果时间注意力与变量注意力，对时间维和变量维进行联合建模。 | 面向可观测性指标等多变量时间序列的零样本预测，如
CPU、内存、网络流量等指标的联合预测。 | 1. 支持单变量和多变量目标预测。<br>2. 输出 0.1～0.9 的固定分位数，使用 p50
中位数作为点预测。<br>3. 支持缓存式块解码，可高效扩展较长预测范围。<br>4. 当前不支持协变量。 |
### 4.4 删除模型
diff --git
a/src/zh/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/zh/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 0a75fce5..45ee65df 100644
---
a/src/zh/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/zh/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2 <sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]
-## 7. Moirai2 模型
+## 7. Toto 模型
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Moirai 2.0）是由 Salesforce AI Research 推出的通用时间序列基础模型（V2.0.10
及以后版本支持）。当前集成的是 Moirai 2.0 R-small 版本，模型参数量约为 11.4M。与采用掩码编码器架构的 Moirai 1.0
不同，Moirai 2.0 使用因果 Decoder-only Patch Transformer，并通过单一 Patch 尺寸、多 Token
预测和多分位数输出，在较小模型规模下实现高效的单变量预测。其核心特性包括：
-
-- **轻量化模型架构**：采用 Decoder-only Patch Transformer，并结合 RMSNorm、旋转位置编码和 SiLU-GLU
前馈网络，在较小参数规模下兼顾预测能力和推理效率。
-- **多 Token 预测**：每个解码步骤可同时预测多个 Patch，减少长预测范围下所需的自回归解码次数。
-- **概率性预测能力**：模型输出 0.1～0.9 共 9 个分位数，AINode 使用 p50 中位数作为点预测结果。
-- **Patch 解码**：在进入注意力模块前，将时间序列按照固定大小的 Patch 进行分组，以提高时序特征提取和解码效率。
-- **实例归一化**：在模型输入前对每条时间序列进行标准化，并在输出后执行反归一化，以缓解不同序列间的分布漂移。
-- **输入范围**：模型聚焦于单变量预测，不支持多变量目标及协变量输入。
-
-
-
-> 注意：Moirai 2.0 R-small 模型权重采用 CC BY-NC 4.0 许可证，仅限研究用途。
-
-## 8. Toto 模型
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
- **单变量与多变量预测**：支持单个目标变量以及多个相关目标变量的联合预测，适用于 CPU、内存、网络流量等可观测性指标的分析场景。
- **概率性预测能力**：模型输出 0.1～0.9 的固定分位数，可刻画预测结果的不确定性；AINode 使用 p50 中位数作为点预测结果。
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821.** [↩ 返回](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ 返回](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref5)
diff --git a/src/zh/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
b/src/zh/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
index 255eaff8..b580ca81 100644
--- a/src/zh/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
+++ b/src/zh/UserGuide/latest/AI-capability/AINode_Upgrade_apache.md
@@ -423,7 +423,6 @@ IoTDB> show models
| sundialx_4| sundial| fine_tuned| training|
| sundialx_5| sundial| fine_tuned| failed|
| chronos2| t5| builtin| inactive|
-| moirai2| moirai| builtin| inactive|
| toto| toto| builtin| inactive|
+---------------------+--------------+--------------+-------------+
```
@@ -448,7 +447,6 @@ IoTDB> show models
| **Timer-XL** | 支持超长上下文的时序大模型，通过大规模工业数据预训练增强泛化能力。 |
需利用极长历史数据的复杂工业预测，如能源、航空航天、交通等领域。 | 1. 超长上下文支持，可处理数万时间点输入。<br>2.
多场景覆盖，支持非平稳、多变量及协变量预测。<br>3. 基于万亿级高质量工业时序数据预训练。
|
| **Timer-Sundial** | 采用“Transformer + TimeFlow”架构的生成式基础模型，专注于概率预测。 |
需要量化不确定性的零样本预测场景，如金融、供应链、新能源发电预测。 | 1. 强大的零样本泛化能力，支持点预测与概率预测 <br>2.
可灵活分析预测分布的任意统计特性。<br>3. 创新生成架构，实现高效的非确定性样本生成。
|
| **Chronos-2** | 基于离散词元化范式的通用时序基础模型，将预测转化为语言建模任务。 |
快速零样本单变量预测，以及可借助协变量（如促销、天气）提升效果的场景。 | 1. 强大的零样本概率预测能力。<br>2.
支持协变量统一建模，但对输入有严格要求：<br> a.
未来协变量的名称组成的集合必须是历史协变量的名称组成的集合的子集；<br> b.
每个历史协变量的长度必须等于目标变量的长度；<br> c. 每个未来协变量的长度必须等于预测长度；<br>3.
采用高效的编码器式结构，兼顾性能与推理速度。 |
-| **Moirai 2.0** | 采用轻量级 Decoder-only Patch Transformer，通过单一 Patch 尺寸、多 Token
预测和多分位数输出实现高效的单变量预测。 | 适用于对模型体量和推理效率要求较高的零样本单变量预测，如工业监测、能源负荷及设备指标预测。 | 1.
模型参数量约 11.4M。<br>2. 每个解码步可预测多个 Patch，降低长预测范围的自回归开销。<br>3. 输出 9 个分位数（0.1～0.9），使用
p50 中位数作为点预测。<br>4. 使用实例归一化缓解序列分布漂移。<br>5. 不支持多变量和协变量。 |
| **Toto 2.0** | 采用 Decoder-only Patch
Transformer，交替使用因果时间注意力与变量注意力，对时间维和变量维进行联合建模。 | 面向可观测性指标等多变量时间序列的零样本预测，如
CPU、内存、网络流量等指标的联合预测。 | 1. 支持单变量和多变量目标预测。<br>2. 输出 0.1～0.9 的固定分位数，使用 p50
中位数作为点预测。<br>3. 支持缓存式块解码，可高效扩展较长预测范围。<br>4. 当前不支持协变量。 |
### 4.4 删除模型
diff --git
a/src/zh/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
b/src/zh/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
index 0a75fce5..45ee65df 100644
---
a/src/zh/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
+++
b/src/zh/UserGuide/latest/AI-capability/TimeSeries-Large-Model_Upgrade_apache.md
@@ -78,24 +78,9 @@ Chronos-2 <sup><a href="#appendix4" id="ref4"
style="text-decoration: none;">[4]
-## 7. Moirai2 模型
+## 7. Toto 模型
-Moirai2<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Moirai 2.0）是由 Salesforce AI Research 推出的通用时间序列基础模型（V2.0.10
及以后版本支持）。当前集成的是 Moirai 2.0 R-small 版本，模型参数量约为 11.4M。与采用掩码编码器架构的 Moirai 1.0
不同，Moirai 2.0 使用因果 Decoder-only Patch Transformer，并通过单一 Patch 尺寸、多 Token
预测和多分位数输出，在较小模型规模下实现高效的单变量预测。其核心特性包括：
-
-- **轻量化模型架构**：采用 Decoder-only Patch Transformer，并结合 RMSNorm、旋转位置编码和 SiLU-GLU
前馈网络，在较小参数规模下兼顾预测能力和推理效率。
-- **多 Token 预测**：每个解码步骤可同时预测多个 Patch，减少长预测范围下所需的自回归解码次数。
-- **概率性预测能力**：模型输出 0.1～0.9 共 9 个分位数，AINode 使用 p50 中位数作为点预测结果。
-- **Patch 解码**：在进入注意力模块前，将时间序列按照固定大小的 Patch 进行分组，以提高时序特征提取和解码效率。
-- **实例归一化**：在模型输入前对每条时间序列进行标准化，并在输出后执行反归一化，以缓解不同序列间的分布漂移。
-- **输入范围**：模型聚焦于单变量预测，不支持多变量目标及协变量输入。
-
-
-
-> 注意：Moirai 2.0 R-small 模型权重采用 CC BY-NC 4.0 许可证，仅限研究用途。
-
-## 8. Toto 模型
-
-Toto<sup><a href="#appendix6" id="ref6" style="text-decoration:
none;">[6]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
+Toto<sup><a href="#appendix5" id="ref5" style="text-decoration:
none;">[5]</a></sup>（Toto 2.0）是由 Datadog 推出的新一代时间序列基础模型（V2.0.10
及以后版本支持），主要面向可观测性场景中的时间序列预测。当前集成的模型采用 2.5B 参数版本，基于 Decoder-only Patch
Transformer 架构，交替使用因果时间注意力与变量注意力，对时间维度和变量维度进行联合建模。其核心特性包括：
- **单变量与多变量预测**：支持单个目标变量以及多个相关目标变量的联合预测，适用于 CPU、内存、网络流量等可观测性指标的分析场景。
- **概率性预测能力**：模型输出 0.1～0.9 的固定分位数，可刻画预测结果的不确定性；AINode 使用 p50 中位数作为点预测结果。
@@ -170,7 +155,6 @@ IoTDB> show models
| timer_xl| timer| builtin| active|
| sundial| sundial| builtin| active|
| chronos2| t5| builtin| active|
-| moirai2| moirai| builtin| active|
| toto| toto| builtin| active|
+---------------------+---------+--------+--------+
```
@@ -185,6 +169,4 @@ IoTDB> show models
<a id="appendix4"></a>**[4]** Chronos-2: From Univariate to Universal
Forecasting, Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer,
Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella,
Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo
Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang,
Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider,
**arXiv:2510.15821.** [↩ 返回](#ref4)
-<a id="appendix5"></a>[5] Moirai 2.0: When Less Is More for Time Series
Forecasting, Salesforce AI Research, arXiv:2511.11698. [↩ 返回](#ref5)
-
-<a id="appendix6"></a>[6] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref6)
+<a id="appendix5"></a>[5] Toto 2.0: Time Series Forecasting Enters the Scaling
Era, Datadog, arXiv:2605.20119. [↩ 返回](#ref5)
