docs: update deepseek v3 example (#2592)

benchmark/deepseek_v3/README.md

@@ -25,3 +25,33 @@ pip install "sglang[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/
 # Launch
 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3-Base --enable-dp-attention --tp 8 --trust-remote-code
 ```
+
+### Example with OpenAI API
+
+```python3
+import openai
+client = openai.Client(
+    base_url="http://127.0.0.1:30000/v1", api_key="EMPTY")
+
+# Chat completion
+response = client.chat.completions.create(
+    model="default",
+    messages=[
+        {"role": "system", "content": "You are a helpful AI assistant"},
+        {"role": "user", "content": "List 3 countries and their capitals."},
+    ],
+    temperature=0,
+    max_tokens=64,
+)
+print(response)
+```
+
+## DeepSeek V3 optimization plan
+
+https://github.com/sgl-project/sglang/issues/2591
+
+## Appendix
+
+SGLang is the inference engine officially recommended by the DeepSeek team.
+
+https://github.com/deepseek-ai/DeepSeek-V3/tree/main?tab=readme-ov-file#62-inference-with-sglang-recommended

python/pyproject.toml

@@ -23,7 +23,7 @@ runtime_common = ["aiohttp", "decord", "fastapi",
     "psutil", "pydantic", "python-multipart",
     "pyzmq>=25.1.2", "torchao>=0.7.0", "uvicorn", "uvloop",
     "xgrammar>=0.1.6"]
-srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post8"]
+srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post9"]
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20241022, not from public vllm whl

python/sglang/srt/layers/moe/topk.py

+# Copyright 2024 SGLang Team
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+
 from typing import Callable, Optional
 
 import torch

python/sglang/srt/layers/quantization/fp8_kernel.py

+# Copyright 2024 SGLang Team
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+
 from typing import List, Tuple
 
 import torch