From 4ecd9afde9787cb0263fd0fcbf5bac5867c17b0f Mon Sep 17 00:00:00 2001 From: zijiexia <37504505+zijiexia@users.noreply.github.com> Date: Tue, 20 Jan 2026 12:31:10 -0800 Subject: [PATCH] [Docs] Rename SGLang Router to SGLang Model Gateway (#17436) --- docs/advanced_features/hyperparameter_tuning.md | 2 +- docs/advanced_features/pd_disaggregation.md | 2 +- docs/advanced_features/server_arguments.md | 2 +- docs/platforms/ascend_npu_deepseek_example.md | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/advanced_features/hyperparameter_tuning.md b/docs/advanced_features/hyperparameter_tuning.md index d9461e19a..2cdae90b6 100644 --- a/docs/advanced_features/hyperparameter_tuning.md +++ b/docs/advanced_features/hyperparameter_tuning.md @@ -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 diff --git a/docs/advanced_features/pd_disaggregation.md b/docs/advanced_features/pd_disaggregation.md index 908129efd..21ea7dffe 100644 --- a/docs/advanced_features/pd_disaggregation.md +++ b/docs/advanced_features/pd_disaggregation.md @@ -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 diff --git a/docs/advanced_features/server_arguments.md b/docs/advanced_features/server_arguments.md index b1b30d4a9..b26619e81 100644 --- a/docs/advanced_features/server_arguments.md +++ b/docs/advanced_features/server_arguments.md @@ -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 diff --git a/docs/platforms/ascend_npu_deepseek_example.md b/docs/platforms/ascend_npu_deepseek_example.md index a3beb31b2..efa57ae3c 100644 --- a/docs/platforms/ascend_npu_deepseek_example.md +++ b/docs/platforms/ascend_npu_deepseek_example.md @@ -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 \