EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

smaller and non gated models for docs (#5378)

Browse Source
This commit is contained in:
simveit
2025-04-21 02:38:25 +02:00
committed by GitHub
parent fac17acf08
commit 8de53da989
6 changed files with 51 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/backend/native_api.ipynb
View File

@@ -49,7 +49,7 @@
"\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --host 0.0.0.0\"\n",
" \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
@@ -105,9 +105,9 @@
"response = requests.get(url)\n",
"response_json = response.json()\n",
"print_highlight(response_json)\n",
"assert response_json[\"model_path\"] == \"meta-llama/Llama-3.2-1B-Instruct\"\n",
"assert response_json[\"model_path\"] == \"qwen/qwen2.5-0.5b-instruct\"\n",
"assert response_json[\"is_generation\"] is True\n",
"assert response_json[\"tokenizer_path\"] == \"meta-llama/Llama-3.2-1B-Instruct\"\n",
"assert response_json[\"tokenizer_path\"] == \"qwen/qwen2.5-0.5b-instruct\"\n",
"assert response_json.keys() == {\"model_path\", \"is_generation\", \"tokenizer_path\"}"
]
},
@@ -213,7 +213,7 @@
"# successful update with same architecture and size\n",
"\n",
"url = f\"http://localhost:{port}/update_weights_from_disk\"\n",
"data = {\"model_path\": \"meta-llama/Llama-3.2-1B\"}\n",
"data = {\"model_path\": \"qwen/qwen2.5-0.5b-instruct\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"print_highlight(response.text)\n",
@@ -230,7 +230,7 @@
"# failed update with different parameter size or wrong name\n",
"\n",
"url = f\"http://localhost:{port}/update_weights_from_disk\"\n",
"data = {\"model_path\": \"meta-llama/Llama-3.2-1B-wrong\"}\n",
"data = {\"model_path\": \"qwen/qwen2.5-0.5b-instruct-wrong\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"response_json = response.json()\n",
@@ -238,11 +238,20 @@
"assert response_json[\"success\"] is False\n",
"assert response_json[\"message\"] == (\n",
" \"Failed to get weights iterator: \"\n",
" \"meta-llama/Llama-3.2-1B-wrong\"\n",
" \"qwen/qwen2.5-0.5b-instruct-wrong\"\n",
" \" (repository not found).\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)"
]
},
{
"cell_type": "markdown",
"metadata": {},
@@ -259,11 +268,9 @@
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)\n",
"\n",
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
"python3 -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-1.5B-instruct \\\n",
" --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
@@ -280,7 +287,7 @@
"# successful encode for embedding model\n",
"\n",
"url = f\"http://localhost:{port}/encode\"\n",
"data = {\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"text\": \"Once upon a time\"}\n",
"data = {\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"text\": \"Once upon a time\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"response_json = response.json()\n",
@@ -318,7 +325,7 @@
"\n",
"reward_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 --host 0.0.0.0 --is-embedding\n",
"python3 -m sglang.launch_server --model-path Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
"\n",
@@ -383,7 +390,7 @@
"outputs": [],
"source": [
"expert_record_server_process, port = launch_server_cmd(\n",
" \"python -m sglang.launch_server --model-path Qwen/Qwen1.5-MoE-A2.7B --host 0.0.0.0\"\n",
" \"python3 -m sglang.launch_server --model-path Qwen/Qwen1.5-MoE-A2.7B --host 0.0.0.0\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
@@ -449,7 +456,7 @@
"source": [
"tokenizer_free_server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --skip-tokenizer-init\n",
"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --skip-tokenizer-init\n",
"\"\"\"\n",
")\n",
"\n",
@@ -464,7 +471,7 @@
"source": [
"from transformers import AutoTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Llama-3.2-1B-Instruct\")\n",
"tokenizer = AutoTokenizer.from_pretrained(\"qwen/qwen2.5-0.5b-instruct\")\n",
"\n",
"input_text = \"What is the capital of France?\"\n",
"\n",

2
docs/backend/offline_engine_api.ipynb
View File

@@ -83,7 +83,7 @@
" nest_asyncio.apply()\n",
"\n",
"\n",
"llm = sgl.Engine(model_path=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")"
"llm = sgl.Engine(model_path=\"qwen/qwen2.5-0.5b-instruct\")"
]
},
{

20
docs/backend/openai_api_completions.ipynb
View File

@@ -44,7 +44,7 @@
"\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0\"\n",
" \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0 --mem-fraction-static 0.8\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
@@ -75,7 +75,7 @@
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
" ],\n",
@@ -104,7 +104,7 @@
"outputs": [],
"source": [
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" messages=[\n",
" {\n",
" \"role\": \"system\",\n",
@@ -143,7 +143,7 @@
"outputs": [],
"source": [
"stream = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" messages=[{\"role\": \"user\", \"content\": \"Say this is a test\"}],\n",
" stream=True,\n",
")\n",
@@ -169,7 +169,7 @@
"outputs": [],
"source": [
"response = client.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" prompt=\"List 3 countries and their capitals.\",\n",
" temperature=0,\n",
" max_tokens=64,\n",
@@ -198,7 +198,7 @@
"outputs": [],
"source": [
"response = client.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" prompt=\"Write a short story about a space explorer.\",\n",
" temperature=0.7, # Moderate temperature for creative writing\n",
" max_tokens=150, # Longer response for a story\n",
@@ -257,7 +257,7 @@
" \"method\": \"POST\",\n",
" \"url\": \"/chat/completions\",\n",
" \"body\": {\n",
" \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" \"model\": \"qwen/qwen2.5-0.5b-instruct\",\n",
" \"messages\": [\n",
" {\"role\": \"user\", \"content\": \"Tell me a joke about programming\"}\n",
" ],\n",
@@ -269,7 +269,7 @@
" \"method\": \"POST\",\n",
" \"url\": \"/chat/completions\",\n",
" \"body\": {\n",
" \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" \"model\": \"qwen/qwen2.5-0.5b-instruct\",\n",
" \"messages\": [{\"role\": \"user\", \"content\": \"What is Python?\"}],\n",
" \"max_tokens\": 50,\n",
" },\n",
@@ -362,7 +362,7 @@
" \"method\": \"POST\",\n",
" \"url\": \"/chat/completions\",\n",
" \"body\": {\n",
" \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" \"model\": \"qwen/qwen2.5-0.5b-instruct\",\n",
" \"messages\": [\n",
" {\n",
" \"role\": \"system\",\n",
@@ -439,7 +439,7 @@
" \"method\": \"POST\",\n",
" \"url\": \"/chat/completions\",\n",
" \"body\": {\n",
" \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" \"model\": \"qwen/qwen2.5-0.5b-instruct\",\n",
" \"messages\": [\n",
" {\n",
" \"role\": \"system\",\n",

12
docs/backend/openai_api_embeddings.ipynb
View File

@@ -40,7 +40,7 @@
"\n",
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
"python3 -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-1.5B-instruct \\\n",
" --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
@@ -66,7 +66,7 @@
"text = \"Once upon a time\"\n",
"\n",
"curl_text = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
"\n",
"text_embedding = json.loads(subprocess.check_output(curl_text, shell=True))[\"data\"][0][\n",
" \"embedding\"\n",
@@ -94,7 +94,7 @@
"\n",
"response = requests.post(\n",
" f\"http://localhost:{port}/v1/embeddings\",\n",
" json={\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": text},\n",
" json={\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": text},\n",
")\n",
"\n",
"text_embedding = response.json()[\"data\"][0][\"embedding\"]\n",
@@ -121,7 +121,7 @@
"\n",
"# Text embedding example\n",
"response = client.embeddings.create(\n",
" model=\"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
" model=\"Alibaba-NLP/gte-Qwen2-1.5B-instruct\",\n",
" input=text,\n",
")\n",
"\n",
@@ -150,11 +150,11 @@
"\n",
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"Alibaba-NLP/gte-Qwen2-7B-instruct\")\n",
"tokenizer = AutoTokenizer.from_pretrained(\"Alibaba-NLP/gte-Qwen2-1.5B-instruct\")\n",
"input_ids = tokenizer.encode(text)\n",
"\n",
"curl_ids = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
"\n",
"input_ids_embedding = json.loads(subprocess.check_output(curl_ids, shell=True))[\"data\"][\n",
" 0\n",

14
docs/backend/openai_api_vision.ipynb
View File

@@ -29,7 +29,7 @@
"\n",
"Launch the server in your terminal and wait for it to initialize.\n",
"\n",
"**Remember to add** `--chat-template llama_3_vision` **to specify the [vision chat template](https://docs.sglang.ai/backend/openai_api_vision.html#Chat-Template), otherwise, the server will only support text (images won’t be passed in), which can lead to degraded performance.**\n",
"**Remember to add** `--chat-template` **for example** `--chat-template=qwen2-vl` **to specify the [vision chat template](https://docs.sglang.ai/backend/openai_api_vision.html#Chat-Template), otherwise, the server will only support text (images won’t be passed in), which can lead to degraded performance.**\n",
"\n",
"We need to specify `--chat-template` for vision language models because the chat template provided in Hugging Face tokenizer only supports text."
]
@@ -51,8 +51,8 @@
"\n",
"vision_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-11B-Vision-Instruct \\\n",
" --chat-template=llama_3_vision\n",
"python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-7B-Instruct \\\n",
" --chat-template=qwen2-vl\n",
"\"\"\"\n",
")\n",
"\n",
@@ -79,7 +79,7 @@
"curl_command = f\"\"\"\n",
"curl -s http://localhost:{port}/v1/chat/completions \\\\\n",
" -d '{{\n",
" \"model\": \"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
" \"model\": \"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
" \"messages\": [\n",
" {{\n",
" \"role\": \"user\",\n",
@@ -127,7 +127,7 @@
"url = f\"http://localhost:{port}/v1/chat/completions\"\n",
"\n",
"data = {\n",
" \"model\": \"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
" \"model\": \"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
" \"messages\": [\n",
" {\n",
" \"role\": \"user\",\n",
@@ -167,7 +167,7 @@
"client = OpenAI(base_url=f\"http://localhost:{port}/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
" model=\"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",
@@ -211,7 +211,7 @@
"client = OpenAI(base_url=f\"http://localhost:{port}/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
" model=\"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",

12
docs/backend/send_request.ipynb
View File

@@ -35,11 +35,11 @@
"\n",
"# This is equivalent to running the following command in your terminal\n",
"\n",
"# python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0\n",
"# python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct \\\n",
" --host 0.0.0.0\n",
"\"\"\"\n",
")\n",
@@ -65,7 +65,7 @@
"curl_command = f\"\"\"\n",
"curl -s http://localhost:{port}/v1/chat/completions \\\n",
" -H \"Content-Type: application/json\" \\\n",
" -d '{{\"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\", \"messages\": [{{\"role\": \"user\", \"content\": \"What is the capital of France?\"}}]}}'\n",
" -d '{{\"model\": \"qwen/qwen2.5-0.5b-instruct\", \"messages\": [{{\"role\": \"user\", \"content\": \"What is the capital of France?\"}}]}}'\n",
"\"\"\"\n",
"\n",
"response = json.loads(subprocess.check_output(curl_command, shell=True))\n",
@@ -90,7 +90,7 @@
"url = f\"http://localhost:{port}/v1/chat/completions\"\n",
"\n",
"data = {\n",
" \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" \"model\": \"qwen/qwen2.5-0.5b-instruct\",\n",
" \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n",
"}\n",
"\n",
@@ -116,7 +116,7 @@
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
" ],\n",
@@ -145,7 +145,7 @@
"\n",
"# Use stream=True for streaming responses\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
" model=\"qwen/qwen2.5-0.5b-instruct\",\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
" ],\n",