Fix docs (#2164)

README.md

@@ -41,15 +41,10 @@ The core features include:
 - **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
 
 ## Getting Started
-Install SGLang: See [https://sgl-project.github.io/start/install.html](https://sgl-project.github.io/start/install.html)
-
-Send requests: See [https://sgl-project.github.io/start/send_request.html](https://sgl-project.github.io/start/send_request.html)
-
-## Backend: SGLang Runtime (SRT)
-See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
-
-## Frontend: Structured Generation Language (SGLang)
-See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
+- [Install SGLang](https://sgl-project.github.io/start/install.html)
+- [Send requests](https://sgl-project.github.io/start/send_request.html)
+- [Backend: SGLang Runtime (SRT)](https://sgl-project.github.io/backend/backend.html)
+- [Frontend: Structured Generation Language (SGLang)](https://sgl-project.github.io/frontend/frontend.html)
 
 ## Benchmark And Performance
 Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)
@@ -57,6 +52,9 @@ Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-s
 ## Roadmap
 [Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
 
-## Citation And Acknowledgment
+## Adoption and Sponsorship
+The project is supported by (alphabetically): AMD, Baseten, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, NVIDIA, RunPod, Stanford, UC Berkeley, and xAI.
+
+## Acknowledgment and Citation
+We learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
 Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
-We also learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).

docs/backend/offline_engine_api.ipynb

@@ -39,7 +39,6 @@
     "# launch the offline engine\n",
     "\n",
     "import sglang as sgl\n",
-    "from sglang.utils import print_highlight\n",
     "import asyncio\n",
     "\n",
     "llm = sgl.Engine(model_path=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")"
@@ -69,8 +68,8 @@
     "\n",
     "outputs = llm.generate(prompts, sampling_params)\n",
     "for prompt, output in zip(prompts, outputs):\n",
-    "    print_highlight(\"===============================\")\n",
-    "    print_highlight(f\"Prompt: {prompt}\\nGenerated text: {output['text']}\")"
+    "    print(\"===============================\")\n",
+    "    print(f\"Prompt: {prompt}\\nGenerated text: {output['text']}\")"
    ]
   },
   {
@@ -93,10 +92,10 @@
     "]\n",
     "sampling_params = {\"temperature\": 0.8, \"top_p\": 0.95}\n",
     "\n",
-    "print_highlight(\"\\n=== Testing synchronous streaming generation ===\")\n",
+    "print(\"\\n=== Testing synchronous streaming generation ===\")\n",
     "\n",
     "for prompt in prompts:\n",
-    "    print_highlight(f\"\\nPrompt: {prompt}\")\n",
+    "    print(f\"\\nPrompt: {prompt}\")\n",
     "    print(\"Generated text: \", end=\"\", flush=True)\n",
     "\n",
     "    for chunk in llm.generate(prompt, sampling_params, stream=True):\n",
@@ -125,15 +124,15 @@
     "\n",
     "sampling_params = {\"temperature\": 0.8, \"top_p\": 0.95}\n",
     "\n",
-    "print_highlight(\"\\n=== Testing asynchronous batch generation ===\")\n",
+    "print(\"\\n=== Testing asynchronous batch generation ===\")\n",
     "\n",
     "\n",
     "async def main():\n",
     "    outputs = await llm.async_generate(prompts, sampling_params)\n",
     "\n",
     "    for prompt, output in zip(prompts, outputs):\n",
-    "        print_highlight(f\"\\nPrompt: {prompt}\")\n",
-    "        print_highlight(f\"Generated text: {output['text']}\")\n",
+    "        print(f\"\\nPrompt: {prompt}\")\n",
+    "        print(f\"Generated text: {output['text']}\")\n",
     "\n",
     "\n",
     "asyncio.run(main())"
@@ -159,12 +158,12 @@
     "]\n",
     "sampling_params = {\"temperature\": 0.8, \"top_p\": 0.95}\n",
     "\n",
-    "print_highlight(\"\\n=== Testing asynchronous streaming generation ===\")\n",
+    "print(\"\\n=== Testing asynchronous streaming generation ===\")\n",
     "\n",
     "\n",
     "async def main():\n",
     "    for prompt in prompts:\n",
-    "        print_highlight(f\"\\nPrompt: {prompt}\")\n",
+    "        print(f\"\\nPrompt: {prompt}\")\n",
     "        print(\"Generated text: \", end=\"\", flush=True)\n",
     "\n",
     "        generator = await llm.async_generate(prompt, sampling_params, stream=True)\n",