chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[Docs] Rename SGLang Router to SGLang Model Gateway (#17436)

Browse Source
This commit is contained in:
zijiexia
2026-01-20 12:31:10 -08:00
committed by GitHub
parent eb38d64413
commit 4ecd9afde9
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/advanced_features/hyperparameter_tuning.md
View File

@@ -67,7 +67,7 @@ Note that CUDA graph consumes more memory, so you may need to reduce `--mem-frac
### Tune `--dp-size` and `--tp-size`
Data parallelism is better for throughput. When there is enough GPU memory, always favor data parallelism for throughput. Refer to [sglang router](../advanced_features/router.md) for a better data parallelism rather than using `dp_size` parameter.
Data parallelism is better for throughput. When there is enough GPU memory, always favor data parallelism for throughput. Refer to [SGLang Model Gateway (former Router)](../advanced_features/sgl_model_gateway.md) for a better data parallelism rather than using `dp_size` parameter.
### Try other options

2
docs/advanced_features/pd_disaggregation.md
View File

@@ -23,7 +23,7 @@ When you need to profile prefill or decode workers in PD disaggregation mode, pl
## Router Integration
For deploying PD disaggregation at scale with load balancing and fault tolerance, SGLang provides a router. The router can distribute requests between prefill and decode instances using various routing policies. For detailed information on setting up routing with PD disaggregation, including configuration options and deployment patterns, see the [SGLang Router documentation](router.md#mode-3-prefill-decode-disaggregation).
For deploying PD disaggregation at scale with load balancing and fault tolerance, SGLang provides a router. The router can distribute requests between prefill and decode instances using various routing policies. For detailed information on setting up routing with PD disaggregation, including configuration options and deployment patterns, see the [SGLang Model Gateway (former Router)](../advanced_features/sgl_model_gateway.md#prefill-decode-disaggregation).
## Mooncake

2
docs/advanced_features/server_arguments.md
View File

@@ -31,7 +31,7 @@ You can find all arguments by `python3 -m sglang.launch_server --help`
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 2
```
- To enable multi-GPU data parallelism, add `--dp 2`. Data parallelism is better for throughput if there is enough memory. It can also be used together with tensor parallelism. The following command uses 4 GPUs in total. We recommend [SGLang Router](../advanced_features/router.md) for data parallelism.
- To enable multi-GPU data parallelism, add `--dp 2`. Data parallelism is better for throughput if there is enough memory. It can also be used together with tensor parallelism. The following command uses 4 GPUs in total. We recommend [SGLang Model Gateway (former Router)](../advanced_features/sgl_model_gateway.md) for data parallelism.
```bash
python -m sglang_router.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --dp 2 --tp 2

4
docs/platforms/ascend_npu_deepseek_example.md
View File

@@ -164,7 +164,7 @@ python -m sglang.launch_server \
--tokenizer-worker-num 4
```
3. SGLang Router
3. SGLang Model Gateway (former Router)
```shell
python -m sglang_router.launch_router \
@@ -297,7 +297,7 @@ do
done
```
3. SGLang Router:
3. SGLang Model Gateway (former Router):
```shell
python -m sglang_router.launch_router \