chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Revert "tiny remove deprecated endpoint call" (#14533)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-12-05 23:48:54 -08:00
committed by GitHub
parent d257bf87b9
commit 42fcf5438f
36 changed files with 59 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/router.md
+1 -1
View File
@@ -45,7 +45,7 @@ SGLang Model Gateway is a high-performance model-routing gateway for large-scale
## Architecture
### Control Plane
- **Worker Manager** discovers capabilities (`/server_info`, `/model_info`), tracks load, and registers/removes workers in the shared registry.
- **Worker Manager** discovers capabilities (`/get_server_info`, `/get_model_info`), tracks load, and registers/removes workers in the shared registry.
- **Job Queue** serializes add/remove requests and exposes status (`/workers/{url}`) so clients can track onboarding progress.
- **Load Monitor** feeds cache-aware and power-of-two policies with live worker load statistics.
- **Health Checker** continuously probes workers and updates readiness, circuit breaker state, and router metrics.
docs/advanced_features/server_arguments.md
+1 -1
View File
@@ -219,7 +219,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| Argument | Description | Defaults | Options |
| --- | --- | --- | --- |
| `--json-model-override-args` | A dictionary in JSON string format used to override default model configurations. | `{}` | Type: str |
| `--preferred-sampling-params` | json-formatted sampling settings that will be returned in /model_info | `None` | Type: str |
| `--preferred-sampling-params` | json-formatted sampling settings that will be returned in /get_model_info | `None` | Type: str |
## LoRA
| Argument | Description | Defaults | Options |