Skip to content

[FLINK-38857][Model] Introduce a Triton inference module under flink-models for batch-oriented AI inference #27385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
featzhang wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[FLINK-38857][Model] Introduce a Triton inference module under flink-models for batch-oriented AI inference #27385

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
422 changes: 422 additions & 0 deletions docs/content.zh/docs/connectors/models/triton.md
View file
Open in desktop

Large diffs are not rendered by default.

15 changes: 15 additions & 0 deletions docs/content.zh/docs/dev/table/sql/create.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -968,4 +968,19 @@ WITH (
);
```

```sql
CREATE MODEL triton_text_classifier
INPUT (input STRING COMMENT '用于分类的输入文本')
OUTPUT (output STRING COMMENT '分类结果')
COMMENT '基于 Triton 的文本分类模型'
WITH (
'provider' = 'triton',
'endpoint' = 'http://localhost:8000/v2/models',
'model-name' = 'text-classification',
'model-version' = '1',
'timeout' = '10000',
'max-retries' = '3'
);
```

{{< top >}}
7 changes: 7 additions & 0 deletions docs/content.zh/docs/dev/table/sql/queries/model-inference.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,4 +131,11 @@ SELECT * FROM ML_PREDICT(
- [模型创建]({{< ref "docs/dev/table/sql/create#create-model" >}})
- [模型修改]({{< ref "docs/dev/table/sql/alter#alter-model" >}})

### 支持的模型提供者

Flink 目前支持以下模型提供者：

- **OpenAI**：用于调用 OpenAI API 服务。详情请参见 [OpenAI 模型文档]({{< ref "docs/connectors/models/openai" >}})。
- **Triton**：用于调用 NVIDIA Triton 推理服务器。详情请参见 [Triton 模型文档]({{< ref "docs/connectors/models/triton" >}})。

{{< top >}}
Loading