Fix formatting in long code blocks (#10528)

docs/advanced_features/attention_backend.md

@@ -29,51 +29,93 @@ The "❌" and "✅" symbols in the table above under "Page Size > 1" indicate wh
 
 - FlashInfer (Default for Non-Hopper Machines, e.g., A100, A40)
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend flashinfer
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-V3 --attention-backend flashinfer --trust-remote-code
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend flashinfer
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-V3 \
+  --attention-backend flashinfer \
+  --trust-remote-code
 ```
 
 - FlashAttention 3 (Default for Hopper Machines, e.g., H100, H200, H20)
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend fa3
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-V3 --trust-remote-code --attention-backend fa3
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend fa3
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-V3 \
+  --trust-remote-code \
+  --attention-backend fa3
 ```
 
 - Triton
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend triton
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-V3 --attention-backend triton --trust-remote-code
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend triton
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-V3 \
+  --attention-backend triton \
+  --trust-remote-code
 ```
 
 - Torch Native
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend torch_native
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend torch_native
 ```
 
 - FlashMLA
 ```bash
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-R1 --attention-backend flashmla --trust-remote-code
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-R1 --attention-backend flashmla --kv-cache-dtype fp8_e4m3 --trust-remote-code
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-R1 \
+  --attention-backend flashmla \
+  --trust-remote-code
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-R1 \
+  --attention-backend flashmla \
+  --kv-cache-dtype fp8_e4m3 \
+  --trust-remote-code
 ```
 
 - TRTLLM MLA (Optimized for Blackwell Architecture, e.g., B200)
 ```bash
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-R1 --attention-backend trtllm_mla --trust-remote-code
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-R1 \
+  --attention-backend trtllm_mla \
+  --trust-remote-code
 ```
 
 - TRTLLM MLA with FP8 KV Cache (Higher concurrency, lower memory footprint)
 ```bash
-python3 -m sglang.launch_server --tp 8 --model deepseek-ai/DeepSeek-R1 --attention-backend trtllm_mla --kv-cache-dtype fp8_e4m3 --trust-remote-code
+python3 -m sglang.launch_server \
+  --tp 8 \
+  --model deepseek-ai/DeepSeek-R1 \
+  --attention-backend trtllm_mla \
+  --kv-cache-dtype fp8_e4m3 \
+  --trust-remote-code
 ```
 
 - Ascend
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend ascend
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend ascend
 ```
 
 - Wave
 ```bash
-python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --attention-backend wave
+python3 -m sglang.launch_server \
+  --model meta-llama/Meta-Llama-3.1-8B-Instruct \
+  --attention-backend wave
 ```
 
 ## Steps to add a new attention backend

docs/advanced_features/pd_disaggregation.md

@@ -34,22 +34,88 @@ uv pip install mooncake-transfer-engine
 ### Llama Single Node
 
 ```bash
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode prefill --disaggregation-ib-device mlx5_roce0
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode decode --port 30001 --base-gpu-id 1 --disaggregation-ib-device mlx5_roce0
-$ python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode prefill \
+  --disaggregation-ib-device mlx5_roce0
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode decode \
+  --port 30001 \
+  --base-gpu-id 1 \
+  --disaggregation-ib-device mlx5_roce0
+python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
 ```
 
 ### DeepSeek Multi-Node
 
 ```bash
 # prefill 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-ib-device ${device_name} --disaggregation-mode prefill --host ${local_ip} --port 30000 --trust-remote-code --dist-init-addr ${prefill_master_ip}:5000 --nnodes 2 --node-rank 0 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-ib-device ${device_name} \
+  --disaggregation-mode prefill \
+  --host ${local_ip} \
+  --port 30000 \
+  --trust-remote-code \
+  --dist-init-addr ${prefill_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 0 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8
 # prefill 1
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-ib-device ${device_name} --disaggregation-mode prefill --host ${local_ip} --port 30000 --trust-remote-code --dist-init-addr ${prefill_master_ip}:5000 --nnodes 2 --node-rank 1 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-ib-device ${device_name} \
+  --disaggregation-mode prefill \
+  --host ${local_ip} \
+  --port 30000 \
+  --trust-remote-code \
+  --dist-init-addr ${prefill_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 1 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8
 # decode 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-ib-device ${device_name} --disaggregation-mode decode --host ${local_ip} --port 30001 --trust-remote-code --dist-init-addr ${decode_master_ip}:5000 --nnodes 2 --node-rank 0 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8 --max-running-requests 128
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-ib-device ${device_name} \
+  --disaggregation-mode decode \
+  --host ${local_ip} \
+  --port 30001 \
+  --trust-remote-code \
+  --dist-init-addr ${decode_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 0 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8 \
+  --max-running-requests 128
 # decode 1
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-ib-device ${device_name} --disaggregation-mode decode --host ${local_ip} --port 30001 --trust-remote-code --dist-init-addr ${decode_master_ip}:5000 --nnodes 2 --node-rank 1 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8 --max-running-requests 128
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-ib-device ${device_name} \
+  --disaggregation-mode decode \
+  --host ${local_ip} \
+  --port 30001 \
+  --trust-remote-code \
+  --dist-init-addr ${decode_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 1 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8 \
+  --max-running-requests 128
 ```
 ### Advanced Configuration
 
@@ -98,22 +164,88 @@ pip install . --config-settings=setup-args="-Ducx_path=/path/to/ucx"
 ### Llama Single Node
 
 ```bash
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode prefill --disaggregation-transfer-backend nixl
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode decode --port 30001 --base-gpu-id 1 --disaggregation-transfer-backend nixl
-$ python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode prefill \
+  --disaggregation-transfer-backend nixl
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode decode \
+  --port 30001 \
+  --base-gpu-id 1 \
+  --disaggregation-transfer-backend nixl
+python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
 ```
 
 ### DeepSeek Multi-Node
 
 ```bash
 # prefill 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend nixl --disaggregation-mode prefill --host ${local_ip} --port 30000 --trust-remote-code --dist-init-addr ${prefill_master_ip}:5000 --nnodes 2 --node-rank 0 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend nixl \
+  --disaggregation-mode prefill \
+  --host ${local_ip} \
+  --port 30000 \
+  --trust-remote-code \
+  --dist-init-addr ${prefill_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 0 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8
 # prefill 1
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend nixl --disaggregation-mode prefill --host ${local_ip} --port 30000 --trust-remote-code --dist-init-addr ${prefill_master_ip}:5000 --nnodes 2 --node-rank 1 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend nixl \
+  --disaggregation-mode prefill \
+  --host ${local_ip} \
+  --port 30000 \
+  --trust-remote-code \
+  --dist-init-addr ${prefill_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 1 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8
 # decode 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend nixl --disaggregation-mode decode --host ${local_ip} --port 30001 --trust-remote-code --dist-init-addr ${decode_master_ip}:5000 --nnodes 2 --node-rank 0 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8 --max-running-requests 128
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend nixl \
+  --disaggregation-mode decode \
+  --host ${local_ip} \
+  --port 30001 \
+  --trust-remote-code \
+  --dist-init-addr ${decode_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 0 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8 \
+  --max-running-requests 128
 # decode 1
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend nixl --disaggregation-mode decode --host ${local_ip} --port 30001 --trust-remote-code --dist-init-addr ${decode_master_ip}:5000 --nnodes 2 --node-rank 1 --tp-size 16 --dp-size 8 --enable-dp-attention --moe-a2a-backend deepep --mem-fraction-static 0.8 --max-running-requests 128
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend nixl \
+  --disaggregation-mode decode \
+  --host ${local_ip} \
+  --port 30001 \
+  --trust-remote-code \
+  --dist-init-addr ${decode_master_ip}:5000 \
+  --nnodes 2 \
+  --node-rank 1 \
+  --tp-size 16 \
+  --dp-size 8 \
+  --enable-dp-attention \
+  --moe-a2a-backend deepep \
+  --mem-fraction-static 0.8 \
+  --max-running-requests 128
 ```
 
 ## ASCEND
@@ -135,16 +267,44 @@ export ENABLE_ASCEND_TRANSFER_WITH_MOONCAKE=true
 ### Llama Single Node
 
 ```bash
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode prefill --disaggregation-transfer-backend ascend
-$ python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --disaggregation-mode decode --port 30001 --base-gpu-id 1 --disaggregation-transfer-backend ascend
-$ python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode prefill \
+  --disaggregation-transfer-backend ascend
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-3.1-8B-Instruct \
+  --disaggregation-mode decode \
+  --port 30001 \
+  --base-gpu-id 1 \
+  --disaggregation-transfer-backend ascend
+python -m sglang_router.launch_router --pd-disaggregation --prefill http://127.0.0.1:30000 --decode http://127.0.0.1:30001 --host 0.0.0.0 --port 8000
 ```
 
 ### DeepSeek Multi-Node
 
 ```bash
 # prefill 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend ascend --disaggregation-mode prefill --host ${local_ip} --port 30000 --trust-remote-code --dist-init-addr ${prefill_master_ip}:5000 --nnodes 1 --node-rank 0 --tp-size 16
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend ascend \
+  --disaggregation-mode prefill \
+  --host ${local_ip} \
+  --port 30000 \
+  --trust-remote-code \
+  --dist-init-addr ${prefill_master_ip}:5000 \
+  --nnodes 1 \
+  --node-rank 0 \
+  --tp-size 16
 # decode 0
-$ python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --disaggregation-transfer-backend ascend --disaggregation-mode decode --host ${local_ip} --port 30001 --trust-remote-code --dist-init-addr ${decode_master_ip}:5000 --nnodes 1 --node-rank 0 --tp-size 16
+python -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --disaggregation-transfer-backend ascend \
+  --disaggregation-mode decode \
+  --host ${local_ip} \
+  --port 30001 \
+  --trust-remote-code \
+  --dist-init-addr ${decode_master_ip}:5000 \
+  --nnodes 1 \
+  --node-rank 0 \
+  --tp-size 16
 ```

docs/advanced_features/server_arguments.md

@@ -43,10 +43,20 @@ You can find all arguments by `python3 -m sglang.launch_server --help`
 
   ```bash
   # Node 0
-  python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --dist-init-addr sgl-dev-0:50000 --nnodes 2 --node-rank 0
+  python -m sglang.launch_server \
+    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
+    --tp 4 \
+    --dist-init-addr sgl-dev-0:50000 \
+    --nnodes 2 \
+    --node-rank 0
 
   # Node 1
-  python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --dist-init-addr sgl-dev-0:50000 --nnodes 2 --node-rank 1
+  python -m sglang.launch_server \
+    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
+    --tp 4 \
+    --dist-init-addr sgl-dev-0:50000 \
+    --nnodes 2 \
+    --node-rank 1
   ```
 
 Please consult the documentation below and [server_args.py](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/server_args.py) to learn more about the arguments you may provide when launching a server.

docs/basic_usage/deepseek.md

@@ -158,7 +158,14 @@ The precompilation process typically takes around 10 minutes to complete.
 **Usage**:
 Add arguments `--speculative-algorithm`, `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` to enable this feature. For example:
 ```
-python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --speculative-algorithm EAGLE --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 --trust-remote-code --tp 8
+python3 -m sglang.launch_server \
+  --model-path deepseek-ai/DeepSeek-V3-0324 \
+  --speculative-algorithm EAGLE \
+  --speculative-num-steps 1 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 2 \
+  --trust-remote-code \
+  --tp 8
 ```
 - The best configuration for `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` can be searched with [bench_speculative.py](https://github.com/sgl-project/sglang/blob/main/scripts/playground/bench_speculative.py) script for given batch size. The minimum configuration is `--speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2`, which can achieve speedup for larger batch sizes.
 - FlashAttention3, FlashMLA, and Triton backend fully supports MTP usage. For FlashInfer backend (`--attention-backend flashinfer`) with speculative decoding,`--speculative-eagle-topk` parameter should be set to `1`. MTP support for the CutlassMLA and TRTLLM MLA backends are still under development.
@@ -177,7 +184,14 @@ See [Reasoning Parser](https://docs.sglang.ai/advanced_features/separate_reasoni
 Add arguments `--tool-call-parser deepseekv3` and `--chat-template ./examples/chat_template/tool_chat_template_deepseekv3.jinja`(recommended) to enable this feature. For example (running on 1 * H20 node):
 
 ```
-python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3-0324 --tp 8 --port 30000 --host 0.0.0.0 --mem-fraction-static 0.9 --tool-call-parser deepseekv3 --chat-template ./examples/chat_template/tool_chat_template_deepseekv3.jinja
+python3 -m sglang.launch_server \
+  --model deepseek-ai/DeepSeek-V3-0324 \
+  --tp 8 \
+  --port 30000 \
+  --host 0.0.0.0 \
+  --mem-fraction-static 0.9 \
+  --tool-call-parser deepseekv3 \
+  --chat-template ./examples/chat_template/tool_chat_template_deepseekv3.jinja
 ```
 
 Sample Request:

docs/basic_usage/gpt_oss.md

@@ -43,7 +43,12 @@ export PYTHON_EXECUTION_BACKEND=UV
 
 Launch the server with the demo tool server:
 
-`python3 -m sglang.launch_server --model-path openai/gpt-oss-120b --tool-server demo --tp 2`
+```bash
+python3 -m sglang.launch_server \
+  --model-path openai/gpt-oss-120b \
+  --tool-server demo \
+  --tp 2
+```
 
 For production usage, sglang can act as an MCP client for multiple services. An [example tool server](https://github.com/openai/gpt-oss/tree/main/gpt-oss-mcp-server) is provided. Start the servers and point sglang to them:
 ```bash

docs/basic_usage/llama4.md

@@ -11,7 +11,10 @@ Ongoing optimizations are tracked in the [Roadmap](https://github.com/sgl-projec
 To serve Llama 4 models on 8xH100/H200 GPUs:
 
 ```bash
-python3 -m sglang.launch_server --model-path meta-llama/Llama-4-Scout-17B-16E-Instruct --tp 8 --context-length 1000000
+python3 -m sglang.launch_server \
+  --model-path meta-llama/Llama-4-Scout-17B-16E-Instruct \
+  --tp 8 \
+  --context-length 1000000
 ```
 
 ### Configuration Tips
@@ -29,7 +32,16 @@ python3 -m sglang.launch_server --model-path meta-llama/Llama-4-Scout-17B-16E-In
 **Usage**:
 Add arguments `--speculative-draft-model-path`, `--speculative-algorithm`, `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` to enable this feature. For example:
 ```
-python3 -m sglang.launch_server --model-path meta-llama/Llama-4-Maverick-17B-128E-Instruct --speculative-algorithm EAGLE3  --speculative-draft-model-path nvidia/Llama-4-Maverick-17B-128E-Eagle3 --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --trust-remote-code --tp 8 --context-length 1000000
+python3 -m sglang.launch_server \
+  --model-path meta-llama/Llama-4-Maverick-17B-128E-Instruct \
+  --speculative-algorithm EAGLE3 \
+  --speculative-draft-model-path nvidia/Llama-4-Maverick-17B-128E-Eagle3 \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --trust-remote-code \
+  --tp 8 \
+  --context-length 1000000
 ```
 
 - **Note** The Llama 4 draft model *nvidia/Llama-4-Maverick-17B-128E-Eagle3* can only recognize conversations in chat mode.
@@ -50,11 +62,21 @@ Commands:
 
 ```bash
 # Llama-4-Scout-17B-16E-Instruct model
-python -m sglang.launch_server --model-path meta-llama/Llama-4-Scout-17B-16E-Instruct --port 30000 --tp 8 --mem-fraction-static 0.8 --context-length 65536
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-4-Scout-17B-16E-Instruct \
+  --port 30000 \
+  --tp 8 \
+  --mem-fraction-static 0.8 \
+  --context-length 65536
 lm_eval --model local-chat-completions --model_args model=meta-llama/Llama-4-Scout-17B-16E-Instruct,base_url=http://localhost:30000/v1/chat/completions,num_concurrent=128,timeout=999999,max_gen_toks=2048 --tasks mmlu_pro --batch_size 128 --apply_chat_template --num_fewshot 0
 
 # Llama-4-Maverick-17B-128E-Instruct
-python -m sglang.launch_server --model-path meta-llama/Llama-4-Maverick-17B-128E-Instruct --port 30000 --tp 8 --mem-fraction-static 0.8 --context-length 65536
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-4-Maverick-17B-128E-Instruct \
+  --port 30000 \
+  --tp 8 \
+  --mem-fraction-static 0.8 \
+  --context-length 65536
 lm_eval --model local-chat-completions --model_args model=meta-llama/Llama-4-Maverick-17B-128E-Instruct,base_url=http://localhost:30000/v1/chat/completions,num_concurrent=128,timeout=999999,max_gen_toks=2048 --tasks mmlu_pro --batch_size 128 --apply_chat_template --num_fewshot 0
 ```
 

docs/basic_usage/qwen3.md

@@ -21,7 +21,13 @@ python3 -m sglang.launch_server --model Qwen/Qwen3-Next-80B-A3B-Instruct --tp 4
 Add arguments `--speculative-algorithm`, `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` to enable this feature. For example:
 
 ``` bash
-python3 -m sglang.launch_server --model Qwen/Qwen3-Next-80B-A3B-Instruct --tp 4 --speculative-num-steps 3  --speculative-eagle-topk 1  --speculative-num-draft-tokens 4 --speculative-algo NEXTN
+python3 -m sglang.launch_server \
+  --model Qwen/Qwen3-Next-80B-A3B-Instruct \
+  --tp 4 \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --speculative-algo NEXTN
 ```
 
 Details can be seen in [this PR](https://github.com/sgl-project/sglang/pull/10233).

docs/basic_usage/sampling_params.md

@@ -258,7 +258,10 @@ Detailed example in [structured outputs](../advanced_features/structured_outputs
 Launch a server with `--enable-custom-logit-processor` flag on.
 
 ```bash
-python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --enable-custom-logit-processor
+python -m sglang.launch_server \
+  --model-path meta-llama/Meta-Llama-3-8B-Instruct \
+  --port 30000 \
+  --enable-custom-logit-processor
 ```
 
 Define a custom logit processor that will always sample a specific token id.

docs/references/custom_chat_template.md

@@ -8,7 +8,10 @@ It should just work for most official models such as Llama-2/Llama-3.
 If needed, you can also override the chat template when launching the server:
 
 ```bash
-python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --chat-template llama-2
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-2-7b-chat-hf \
+  --port 30000 \
+  --chat-template llama-2
 ```
 
 If the chat template you are looking for is missing, you are welcome to contribute it or load it from a file.
@@ -30,7 +33,10 @@ You can load the JSON format, which is defined by `conversation.py`.
 ```
 
 ```bash
-python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --chat-template ./my_model_template.json
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-2-7b-chat-hf \
+  --port 30000 \
+  --chat-template ./my_model_template.json
 ```
 
 ## Jinja Format
@@ -38,5 +44,8 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
 You can also use the [Jinja template format](https://huggingface.co/docs/transformers/main/en/chat_templating) as defined by Hugging Face Transformers.
 
 ```bash
-python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --chat-template ./my_model_template.jinja
+python -m sglang.launch_server \
+  --model-path meta-llama/Llama-2-7b-chat-hf \
+  --port 30000 \
+  --chat-template ./my_model_template.jinja
 ```

docs/references/multi_node_deployment/multi_node.md

@@ -7,9 +7,19 @@
 ```bash
 # replace 172.16.4.52:20000 with your own node ip address and port of the first node
 
-python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 0
+python3 -m sglang.launch_server \
+  --model-path meta-llama/Meta-Llama-3.1-405B-Instruct \
+  --tp 16 \
+  --dist-init-addr 172.16.4.52:20000 \
+  --nnodes 2 \
+  --node-rank 0
 
-python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 1
+python3 -m sglang.launch_server \
+  --model-path meta-llama/Meta-Llama-3.1-405B-Instruct \
+  --tp 16 \
+  --dist-init-addr 172.16.4.52:20000 \
+  --nnodes 2 \
+  --node-rank 1
 ```
 
 Note that LLama 405B (fp8) can also be launched on a single node.

docs/references/production_metrics.md

@@ -139,7 +139,10 @@ This section describes how to set up the monitoring stack (Prometheus + Grafana)
 1.  **Start your SGLang server with metrics enabled:**
 
     ```bash
-    python -m sglang.launch_server --model-path <your_model_path> --port 30000 --enable-metrics
+    python -m sglang.launch_server \
+      --model-path <your_model_path> \
+      --port 30000 \
+      --enable-metrics
     ```
     Replace `<your_model_path>` with the actual path to your model (e.g., `meta-llama/Meta-Llama-3.1-8B-Instruct`). Ensure the server is accessible from the monitoring stack (you might need `--host 0.0.0.0` if running in Docker). By default, the metrics endpoint will be available at `http://<sglang_server_host>:30000/metrics`.
 
@@ -212,6 +215,17 @@ You can customize the setup by modifying these files. For instance, you might ne
 
 #### Check if the metrics are being collected
 
-Run `python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompts 3000 --random-input 1024 --random-output 1024 --random-range-ratio 0.5` to generate some requests.
+Run:
+```
+python3 -m sglang.bench_serving \
+  --backend sglang \
+  --dataset-name random \
+  --num-prompts 3000 \
+  --random-input 1024 \
+  --random-output 1024 \
+  --random-range-ratio 0.5
+```
+
+to generate some requests.
 
 Then you should be able to see the metrics in the Grafana dashboard.