diff --git a/benchmark/deepseek_v3/README.md b/benchmark/deepseek_v3/README.md
index 59459180b..7690410e8 100644
--- a/benchmark/deepseek_v3/README.md
+++ b/benchmark/deepseek_v3/README.md
@@ -168,6 +168,30 @@ If you have two H100 nodes, the usage is similar to the aforementioned H20.
 
 > **Note that the launch command here does not enable Data Parallelism Attention or `torch.compile` Optimization**. For optimal performance, please refer to the command options in [Performance Optimization Options](#option_args).
 
+### Example: Serving with one B200 node
+
+There is one B200 node with 4 (for FP4) GPUs or 8 (for FP4 or FP8) GPUs.  Both FP4 and FP8 models are supported for DeepSeek R1.  The flags to achieve optimal performance for each are slightly different.
+
+#### FP4
+
+If using 4 GPUs:
+
+```bash
+python3 -m sglang.launch_server --model-path nvidia/DeepSeek-R1-0528-FP4-V2 --host 0.0.0.0 --port 8000 --tensor-parallel-size=4 --cuda-graph-max-bs 256 --max-running-requests 256 --mem-fraction-static 0.85 --ep-size 4 --scheduler-recv-interval 30 --enable-symm-mem --stream-interval 10
+```
+
+If using 8 GPUs:
+
+```bash
+python3 -m sglang.launch_server --model-path nvidia/DeepSeek-R1-0528-FP4-V2 --host 0.0.0.0 --port 8000 --tensor-parallel-size=8 --cuda-graph-max-bs 256 --max-running-requests 256 --mem-fraction-static 0.85 --ep-size 8 --scheduler-recv-interval 30 --enable-symm-mem --stream-interval 10
+```
+
+#### FP8
+
+```
+SGLANG_ENABLE_JIT_DEEPGEMM=false SGLANG_ENABLE_FLASHINFER_GEMM=true bash python3 -m sglang.launch_server --model-path=deepseek-ai/DeepSeek-R1-0528 --host=0.0.0.0 --port=8000 --tensor-parallel-size=8 --cuda-graph-max-bs 128 --max-running-requests 128 --mem-fraction-static 0.82 --kv-cache-dtype fp8_e4m3 --chunked-prefill-size 32768 --max-prefill-tokens 32768 --scheduler-recv-interval 30 --stream-interval 30
+```
+
 ### Example: Serving with two H200\*8 nodes and docker
 
 There are two H200 nodes, each with 8 GPUs. The first node's IP is `192.168.114.10`, and the second node's IP is `192.168.114.11`. Configure the endpoint to expose it to another Docker container using `--host 0.0.0.0` and `--port 40000`, and set up communications with `--dist-init-addr 192.168.114.10:20000`.
diff --git a/docs/basic_usage/deepseek_v3.md b/docs/basic_usage/deepseek_v3.md
index 8396b2f50..1e406ee90 100644
--- a/docs/basic_usage/deepseek_v3.md
+++ b/docs/basic_usage/deepseek_v3.md
@@ -12,6 +12,7 @@ To run DeepSeek V3.1/V3/R1 models, the recommended settings are as follows:
 | Weight Type | Configuration |
 |------------|-------------------|
 | **Full precision [FP8](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)**<br>*(recommended)* | 8 x H200 |
+| | 8 x B200 |
 | | 8 x MI300X |
 | | 2 x 8 x H100/800/20 |
 | | Xeon 6980P CPU |
@@ -27,7 +28,7 @@ To run DeepSeek V3.1/V3/R1 models, the recommended settings are as follows:
 | **Quantized weights ([AWQ](https://huggingface.co/QuixiAI/DeepSeek-R1-0528-AWQ))** | 8 x H100/800/20 |
 | | 8 x A100/A800 |
 | **Quantized weights ([MXFP4](https://huggingface.co/amd/DeepSeek-R1-MXFP4-Preview))** | 8, 4 x MI355X/350X |
-| **Quantized weights ([NVFP4](https://huggingface.co/nvidia/DeepSeek-R1-0528-NVFP4))** | 8, 4 x B200 |
+| **Quantized weights ([NVFP4](https://huggingface.co/nvidia/DeepSeek-R1-0528-NVFP4-v2))** | 8, 4 x B200 |
 
 <style>
 .md-typeset__table {
@@ -65,6 +66,7 @@ The official DeepSeek V3 is already in FP8 format, so you should not run it with
 Detailed commands for reference:
 
 - [8 x H200](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#using-docker-recommended)
+- [4 x B200, 8 x B200](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-one-b200-node)
 - [8 x MI300X](../platforms/amd_gpu.md#running-deepseek-v3)
 - [2 x 8 x H200](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-two-h208-nodes)
 - [4 x 8 x A100](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-four-a1008-nodes)