Skip to content

Commit 97bad77

Browse files
authored
docs: roll out guide (#829)
* added rollout guide Signed-off-by: Xiyue Yu <[email protected]> * changed format * changed format * fixed comments and added more examples * seperate files * fixed comment * fixed format * fixed format --------- Signed-off-by: Xiyue Yu <[email protected]>
1 parent 5f95113 commit 97bad77

File tree

4 files changed

+394
-67
lines changed

4 files changed

+394
-67
lines changed

mkdocs.yml

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -61,9 +61,10 @@ nav:
6161
- Guides:
6262
- User Guides:
6363
- Getting started: guides/index.md
64-
- Adapter Rollout: guides/adapter-rollout.md
64+
- Rollout:
65+
- Adapter Rollout: guides/adapter-rollout.md
66+
- InferencePool Rollout: guides/inferencepool-rollout.md
6567
- Metrics: guides/metrics.md
66-
- Replacing an Inference Pool: guides/replacing-inference-pool.md
6768
- Implementer's Guide: guides/implementers.md
6869
- Performance:
6970
- Benchmark: performance/benchmark/index.md

site-src/guides/adapter-rollout.md

Lines changed: 12 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,18 @@
1-
# Adapter Rollout
1+
# Lora Adapter Rollout
22

3-
The goal of this guide is to demonstrate how to rollout a new adapter version.
3+
The goal of this guide is to show you how to perform incremental roll out operations,
4+
which gradually deploy new versions of your inference infrastructure.
5+
You can update LoRA adapters and Inference Pool with minimal service disruption.
6+
This page also provides guidance on traffic splitting and rollbacks to help ensure reliable deployments for LoRA adapters rollout.
47

5-
## **Prerequisites**
6-
7-
Follow the steps in the [main guide](index.md)
8+
LoRA adapter rollouts let you deploy new versions of LoRA adapters in phases,
9+
without altering the underlying base model or infrastructure.
10+
Use LoRA adapter rollouts to test improvements, bug fixes, or new features in your LoRA adapters.
811

12+
## Example
913

10-
## **Safely rollout v2 adapter**
14+
### Prerequisites
15+
Follow the steps in the [main guide](index.md)
1116

1217
### Load the new adapter version to the model servers
1318

@@ -135,3 +140,4 @@ data:
135140
```
136141

137142
With this, all requests should be served by the new adapter version.
143+

0 commit comments

Comments
 (0)