Skip to content

Commit b362f8b

Browse files
committed
[REST] Tweaks
1 parent 2f5bab0 commit b362f8b

File tree

17 files changed

+46
-22
lines changed

17 files changed

+46
-22
lines changed

1_developer/0_core/0_server/settings.md

Lines changed: 11 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ index: 2
88

99
You can configure server settings, such as the port number, whether to allow other API clients to access the server and MCP features.
1010

11-
<img src="/assets/docs/server-config.png" style="" data-caption="Configure LM Studio API Server settings" />
11+
<img src="/assets/docs/server-settings.png" style="" data-caption="Configure LM Studio API Server settings" />
1212

1313

1414
### Settings information
@@ -19,13 +19,21 @@ You can configure server settings, such as the port number, whether to allow oth
1919
optional: false
2020
description: Port number on which the LM Studio API server listens for incoming connections.
2121
unstyledName: true
22+
- name: Require Authentication
23+
type: Switch
24+
description: Require API clients to provide a valid API token via the `Authorization` header. Learn more in the [Authentication](/docs/developer/core/authentication) section.
25+
unstyledName: true
2226
- name: Serve on Local Network
2327
type: Switch
2428
description: Allow other devices on the same local network to access the API server. Learn more in the [Serve on Local Network](/docs/developer/core/server/serve-on-network) section.
2529
unstyledName: true
26-
- name: Allow Per Request Remote MCPs
30+
- name: Allow per-request MCPs
31+
type: Switch
32+
description: Allow API clients to use MCP (Model Control Protocol) servers that are not in your mcp.json. These MCP connections are ephemeral, only existing as long as the request. At the moment, only remote MCPs are supported.
33+
unstyledName: true
34+
- name: Allow calling servers from mcp.json
2735
type: Switch
28-
description: Enable sending requests to remote MCP (Model Control Protocol) servers on a per-request basis.
36+
description: Allow API clients to use servers you defined in your mcp.json in LM Studio. This can be a security risk if you've defined MCP servers that have access to your file system or private data. This option requires "Require Authentication" to be enabled.
2937
unstyledName: true
3038
- name: Enable CORS
3139
type: Switch
File renamed without changes.

1_developer/0_core/headless.md

Lines changed: 5 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -23,26 +23,25 @@ To enable this, head to app settings (`Cmd` / `Ctrl` + `,`) and check the box to
2323

2424
When this setting is enabled, exiting the app will minimize it to the system tray, and the LLM server will continue to run in the background.
2525

26-
## Just-In-Time (JIT) model loading for OpenAI endpoints
26+
## Just-In-Time (JIT) model loading for REST endpoints
2727

2828
Useful when utilizing LM Studio as an LLM service with other frontends or applications.
2929

3030
<img src="/assets/docs/jit-loading.png" style="" data-caption="Load models on demand" />
3131

3232
#### When JIT loading is ON:
3333

34-
- Call to `/v1/models` will return all downloaded models, not only the ones loaded into memory
34+
- Calls to OpenAI-compatible `/v1/models` will return all downloaded models, not only the ones loaded into memory
3535
- Calls to inference endpoints will load the model into memory if it's not already loaded
3636

3737
#### When JIT loading is OFF:
3838

39-
- Call to `/v1/models` will return only the models loaded into memory
39+
- Calls to OpenAI-compatible `/v1/models` will return only the models loaded into memory
4040
- You have to first load the model into memory before being able to use it
4141

42-
##### What about auto unloading?
42+
#### What about auto unloading?
4343

44-
As of LM Studio 0.3.5, auto unloading is not yet in place. Models that are loaded via JIT loading will remain in memory until you unload them.
45-
We expect to implement more sophisticated memory management in the near future. Let us know if you have any feedback or suggestions.
44+
JIT loaded models will be auto-unloaded from memory by default after a set period of inactivity ([learn more](/docs/developer/core/ttl-and-auto-evict)).
4645

4746
## Auto Server Start
4847

1_developer/0_core/_mcp.md renamed to 1_developer/0_core/mcp.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,10 +2,12 @@
22
title: Using MCP via API
33
sidebar_title: Using MCP via API
44
description: Learn how to use Model Control Protocol (MCP) servers with LM Studio API.
5-
index: 4
5+
index: 3
66
---
77

8-
LM Studio supports Model Control Protocol (MCP) usage via API starting from version 0.4.0. MCP allows models to interact with external tools and services through standardized servers.
8+
##### Requires [LM Studio 0.4.0](/download) or newer.
9+
10+
LM Studio supports Model Control Protocol (MCP) usage via API. MCP allows models to interact with external tools and services through standardized servers.
911

1012
## How it works
1113

1_developer/0_core/ttl-and-auto-evict.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Idle TTL and Auto-Evict
33
description: Optionally auto-unload idle models after a certain amount of time (TTL)
4-
index: 1
4+
index: 4
55
---
66

77
## Background
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.

0 commit comments

Comments
 (0)