Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "767f9bdbbb6f2540a33b21ebc23c26526474b01d"
Unverified Commit 72e979bf authored by Chayenne's avatar Chayenne Committed by GitHub
Browse files

add native api docs (#1883) 


Co-authored-by: default avatarChayenne <zhaochenyang@g.ucla.edu>
parent 146f6134
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 319 additions and 1142 deletions
docs/backend/embedding_model.ipynb
View file @ 72e979bf
......@@ -30,7 +30,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-01T02:47:32.337369Z",
......@@ -39,59 +39,7 @@
"shell.execute_reply": "2024-11-01T02:47:59.539861Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
" warnings.warn(\n",
"[2024-10-31 22:40:37] server_args=ServerArgs(model_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='Alibaba-NLP/gte-Qwen2-7B-instruct', chat_template=None, is_embedding=True, host='0.0.0.0', port=30010, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=309155486, constrained_json_whitespace_pattern=None, decode_log_interval=40, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n",
"/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
" warnings.warn(\n",
"/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
" warnings.warn(\n",
"[2024-10-31 22:40:42 TP0] Init torch distributed begin.\n",
"[2024-10-31 22:40:43 TP0] Load weight begin. avail mem=47.27 GB\n",
"[2024-10-31 22:40:43 TP0] lm_eval is not installed, GPTQ may not be usable\n",
"INFO 10-31 22:40:44 weight_utils.py:243] Using model weights format ['*.safetensors']\n",
"Loading safetensors checkpoint shards: 0% Completed | 0/7 [00:00<?, ?it/s]\n",
"Loading safetensors checkpoint shards: 14% Completed | 1/7 [00:00<00:03, 1.97it/s]\n",
"Loading safetensors checkpoint shards: 29% Completed | 2/7 [00:01<00:03, 1.40it/s]\n",
"Loading safetensors checkpoint shards: 43% Completed | 3/7 [00:02<00:03, 1.11it/s]\n",
"Loading safetensors checkpoint shards: 57% Completed | 4/7 [00:03<00:03, 1.00s/it]\n",
"Loading safetensors checkpoint shards: 71% Completed | 5/7 [00:04<00:02, 1.07s/it]\n",
"Loading safetensors checkpoint shards: 86% Completed | 6/7 [00:05<00:01, 1.10s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00, 1.12s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00, 1.02s/it]\n",
"\n",
"[2024-10-31 22:40:51 TP0] Load weight end. type=Qwen2ForCausalLM, dtype=torch.float16, avail mem=32.91 GB\n",
"[2024-10-31 22:40:51 TP0] Memory pool end. avail mem=4.56 GB\n",
"[2024-10-31 22:40:52 TP0] max_total_num_tokens=509971, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n",
"[2024-10-31 22:40:52] INFO: Started server process [1752367]\n",
"[2024-10-31 22:40:52] INFO: Waiting for application startup.\n",
"[2024-10-31 22:40:52] INFO: Application startup complete.\n",
"[2024-10-31 22:40:52] INFO: Uvicorn running on http://0.0.0.0:30010 (Press CTRL+C to quit)\n",
"[2024-10-31 22:40:52] INFO: 127.0.0.1:41676 - \"GET /v1/models HTTP/1.1\" 200 OK\n",
"[2024-10-31 22:40:53] INFO: 127.0.0.1:41678 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
"[2024-10-31 22:40:53 TP0] Prefill batch. #new-seq: 1, #new-token: 6, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-10-31 22:40:54] INFO: 127.0.0.1:41684 - \"POST /encode HTTP/1.1\" 200 OK\n",
"[2024-10-31 22:40:54] The server is fired up and ready to roll!\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'><br><br> NOTE: Typically, the server runs in a separate terminal.<br> In this notebook, we run the server and notebook code together, so their outputs are combined.<br> To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.<br> </strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
......@@ -119,7 +67,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-01T02:47:59.543958Z",
......@@ -128,28 +76,7 @@
"shell.execute_reply": "2024-11-01T02:47:59.590809Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-10-31 22:40:57 TP0] Prefill batch. #new-seq: 1, #new-token: 4, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-10-31 22:40:57] INFO: 127.0.0.1:51746 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>Text embedding (first 10): [0.0083160400390625, 0.0006804466247558594, -0.00809478759765625, -0.0006995201110839844, 0.0143890380859375, -0.0090179443359375, 0.01238250732421875, 0.00209808349609375, 0.0062103271484375, -0.003047943115234375]</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import subprocess, json\n",
"\n",
......@@ -176,7 +103,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-01T02:47:59.594229Z",
......@@ -185,28 +112,7 @@
"shell.execute_reply": "2024-11-01T02:48:00.005255Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-10-31 22:40:58 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 21.43%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-10-31 22:40:58] INFO: 127.0.0.1:51750 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>Text embedding (first 10): [0.00829315185546875, 0.0007004737854003906, -0.00809478759765625, -0.0006799697875976562, 0.01438140869140625, -0.00897979736328125, 0.0123748779296875, 0.0020923614501953125, 0.006195068359375, -0.0030498504638671875]</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import openai\n",
"\n",
......@@ -233,7 +139,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2024-11-01T02:48:00.008858Z",
......@@ -242,36 +148,7 @@
"shell.execute_reply": "2024-11-01T02:48:01.871573Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-10-31 22:41:00 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 33.33%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-10-31 22:41:00] INFO: 127.0.0.1:51762 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>Input IDs embedding (first 10): [0.00829315185546875, 0.0007004737854003906, -0.00809478759765625, -0.0006799697875976562, 0.01438140869140625, -0.00897979736328125, 0.0123748779296875, 0.0020923614501953125, 0.006195068359375, -0.0030498504638671875]</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import json\n",
"import os\n",
......
docs/backend/native_api.ipynb 0 → 100644
View file @ 72e979bf
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Native Server API\n",
"\n",
"Apart from the OpenAI compatible API, the SGLang Runtime also provides its native server API. We introduce these following API:\n",
"\n",
"- `/generate`\n",
"- `/update_weights`\n",
"- `/get_server_args`\n",
"- `/get_model_info`\n",
"- `/health`\n",
"- `/health_generate`\n",
"- `/flush_cache`\n",
"- `/get_memory_pool_size`\n",
"\n",
"We mainly use `requests` to test these APIs in the following examples. You can also use `curl`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Launch A Server"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
" wait_for_server,\n",
" terminate_process,\n",
" print_highlight,\n",
")\n",
"import subprocess, json\n",
"\n",
"server_process = execute_shell_command(\n",
"\"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --port=30010\n",
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30010\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate\n",
"\n",
"Used to generate completion from the model, similar to the `/v1/completions` API in OpenAI. Detailed parameters can be found in the [sampling parameters](https://sgl-project.github.io/references/sampling_params.html)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"\n",
"url = \"http://localhost:30010/generate\"\n",
"data = {\"text\": \"List 3 countries and their capitals.\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"print_highlight(response.text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Get Server Args\n",
"\n",
"Used to get the serving args when the server is launched."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"url = \"http://localhost:30010/get_server_args\"\n",
"\n",
"response = requests.get(url)\n",
"print_highlight(response.json())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Get Model Info\n",
"\n",
"Used to get the model info.\n",
"\n",
"- `model_path`: The path/name of the model.\n",
"- `is_generation`: Whether the model is used as generation model or embedding model."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"url = \"http://localhost:30010/get_model_info\"\n",
"\n",
"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[\"is_generation\"] == True\n",
"assert response_json.keys() == {\"model_path\", \"is_generation\"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Health and Health Generate\n",
"\n",
"- `/health`: Check the health of the server.\n",
"- `/health_generate`: Check the health of the server by generating one token."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"url = \"http://localhost:30010/health_generate\"\n",
"\n",
"response = requests.get(url)\n",
"print_highlight(response.text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"url = \"http://localhost:30010/health\"\n",
"\n",
"response = requests.get(url)\n",
"print_highlight(response.text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Flush Cache\n",
"\n",
"Used to flush the radix cache. It will be automatically triggered when the model weights are updated by the `/update_weights` API."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# flush cache\n",
"\n",
"url = \"http://localhost:30010/flush_cache\"\n",
"\n",
"response = requests.post(url)\n",
"print_highlight(response.text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Get Memory Pool Size\n",
"\n",
"Get the memory pool size in number of tokens.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# get_memory_pool_size\n",
"\n",
"url = \"http://localhost:30010/get_memory_pool_size\"\n",
"\n",
"response = requests.get(url)\n",
"print_highlight(response.text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Update Weights\n",
"\n",
"Update model weights without restarting the server. Use for continuous evaluation during training. Only applicable for models with the same architecture and parameter size."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# successful update with same architecture and size\n",
"\n",
"url = \"http://localhost:30010/update_weights\"\n",
"data = {\"model_path\": \"meta-llama/Llama-3.2-1B\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"print_highlight(response.text)\n",
"assert response.json()[\"success\"] == True\n",
"assert response.json()[\"message\"] == \"Succeeded to update model weights.\"\n",
"assert response.json().keys() == {\"success\", \"message\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# failed update with different parameter size\n",
"\n",
"url = \"http://localhost:30010/update_weights\"\n",
"data = {\"model_path\": \"meta-llama/Llama-3.2-3B\"}\n",
"\n",
"response = requests.post(url, json=data)\n",
"response_json = response.json()\n",
"print_highlight(response_json)\n",
"assert response_json[\"success\"] == False\n",
"assert response_json[\"message\"] == (\n",
" \"Failed to update weights: The size of tensor a (2048) must match \"\n",
" \"the size of tensor b (3072) at non-singleton dimension 1.\\n\"\n",
" \"Rolling back to original weights.\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "AlphaMeemory",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
docs/backend/openai_api_completions.ipynb
View file @ 72e979bf
This diff is collapsed.
docs/backend/openai_api_vision.ipynb
View file @ 72e979bf
......@@ -38,58 +38,7 @@
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-11-02 00:24:10.542705: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:479] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"2024-11-02 00:24:10.554725: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:10575] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"2024-11-02 00:24:10.554758: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1442] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"2024-11-02 00:24:11.063662: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
"[2024-11-02 00:24:19] server_args=ServerArgs(model_path='meta-llama/Llama-3.2-11B-Vision-Instruct', tokenizer_path='meta-llama/Llama-3.2-11B-Vision-Instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='meta-llama/Llama-3.2-11B-Vision-Instruct', chat_template='llama_3_vision', is_embedding=False, host='127.0.0.1', port=30010, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=553831757, constrained_json_whitespace_pattern=None, decode_log_interval=40, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n",
"[2024-11-02 00:24:20] Use chat template for the OpenAI-compatible API server: llama_3_vision\n",
"[2024-11-02 00:24:29 TP0] Automatically turn off --chunked-prefill-size and adjust --mem-fraction-static for multimodal models.\n",
"[2024-11-02 00:24:29 TP0] Init torch distributed begin.\n",
"[2024-11-02 00:24:32 TP0] Load weight begin. avail mem=76.83 GB\n",
"[2024-11-02 00:24:32 TP0] lm_eval is not installed, GPTQ may not be usable\n",
"INFO 11-02 00:24:32 weight_utils.py:243] Using model weights format ['*.safetensors']\n",
"Loading safetensors checkpoint shards: 0% Completed | 0/5 [00:00<?, ?it/s]\n",
"Loading safetensors checkpoint shards: 20% Completed | 1/5 [00:00<00:02, 1.61it/s]\n",
"Loading safetensors checkpoint shards: 40% Completed | 2/5 [00:02<00:04, 1.35s/it]\n",
"Loading safetensors checkpoint shards: 60% Completed | 3/5 [00:04<00:03, 1.58s/it]\n",
"Loading safetensors checkpoint shards: 80% Completed | 4/5 [00:06<00:01, 1.70s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 5/5 [00:08<00:00, 1.76s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 5/5 [00:08<00:00, 1.62s/it]\n",
"\n",
"[2024-11-02 00:24:41 TP0] Load weight end. type=MllamaForConditionalGeneration, dtype=torch.bfloat16, avail mem=56.75 GB\n",
"[2024-11-02 00:24:41 TP0] Memory pool end. avail mem=11.53 GB\n",
"[2024-11-02 00:24:42 TP0] Capture cuda graph begin. This can take up to several minutes.\n",
"[2024-11-02 00:24:52 TP0] max_total_num_tokens=289349, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n",
"[2024-11-02 00:24:52] INFO: Started server process [108249]\n",
"[2024-11-02 00:24:52] INFO: Waiting for application startup.\n",
"[2024-11-02 00:24:52] INFO: Application startup complete.\n",
"[2024-11-02 00:24:52] INFO: Uvicorn running on http://127.0.0.1:30010 (Press CTRL+C to quit)\n",
"[2024-11-02 00:24:53] INFO: 127.0.0.1:43056 - \"GET /v1/models HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:24:53] INFO: 127.0.0.1:43072 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:24:53 TP0] Prefill batch. #new-seq: 1, #new-token: 7, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:24:53] INFO: 127.0.0.1:43086 - \"POST /generate HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:24:53] The server is fired up and ready to roll!\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'><br><br> NOTE: Typically, the server runs in a separate terminal.<br> In this notebook, we run the server and notebook code together, so their outputs are combined.<br> To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.<br> </strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
......@@ -99,7 +48,7 @@
")\n",
"\n",
"embedding_process = execute_shell_command(\n",
"\"\"\"\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-11B-Vision-Instruct \\\n",
" --port=30010 --chat-template=llama_3_vision\n",
"\"\"\"\n",
......@@ -121,44 +70,7 @@
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n",
"100 485 0 0 100 485 0 2420 --:--:-- --:--:-- --:--:-- 2412"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:26:23 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 6462, cache hit rate: 49.97%, token usage: 0.02, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:26:24] INFO: 127.0.0.1:39828 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100 965 100 480 100 485 789 797 --:--:-- --:--:-- --:--:-- 1584\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>{\"id\":\"5e9e1c80809f492a926a2634c3d162d0\",\"object\":\"chat.completion\",\"created\":1730507184,\"model\":\"meta-llama/Llama-3.2-11B-Vision-Instruct\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"The image depicts a man ironing clothes on an ironing board that is placed on the back of a yellow taxi cab.\"},\"logprobs\":null,\"finish_reason\":\"stop\",\"matched_stop\":128009}],\"usage\":{\"prompt_tokens\":6463,\"total_tokens\":6489,\"completion_tokens\":26,\"prompt_tokens_details\":null}}</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import subprocess\n",
"\n",
......@@ -206,29 +118,7 @@
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:26:33 TP0] Prefill batch. #new-seq: 1, #new-token: 11, #cached-token: 6452, cache hit rate: 66.58%, token usage: 0.02, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:26:34 TP0] Decode batch. #running-req: 1, #token: 6477, token usage: 0.02, gen throughput (token/s): 0.77, #queue-req: 0\n",
"[2024-11-02 00:26:34] INFO: 127.0.0.1:43258 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>The image shows a man ironing clothes on the back of a yellow taxi cab.</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"from openai import OpenAI\n",
"\n",
......@@ -246,7 +136,9 @@
" },\n",
" {\n",
" \"type\": \"image_url\",\n",
" \"image_url\": {\"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"},\n",
" \"image_url\": {\n",
" \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"\n",
" },\n",
" },\n",
" ],\n",
" }\n",
......@@ -270,30 +162,7 @@
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:20:30 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 12894, cache hit rate: 83.27%, token usage: 0.04, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:20:30 TP0] Decode batch. #running-req: 1, #token: 12903, token usage: 0.04, gen throughput (token/s): 2.02, #queue-req: 0\n",
"[2024-11-02 00:20:30 TP0] Decode batch. #running-req: 1, #token: 12943, token usage: 0.04, gen throughput (token/s): 105.52, #queue-req: 0\n",
"[2024-11-02 00:20:30] INFO: 127.0.0.1:41386 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>The first image shows a man in a yellow shirt ironing a shirt on the back of a yellow taxi cab, with a red line connecting the two objects. The second image shows a large orange \"S\" and \"G\" on a white background, with a red line connecting them.</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"from openai import OpenAI\n",
"\n",
......@@ -320,7 +189,7 @@
" {\n",
" \"type\": \"text\",\n",
" \"text\": \"I have two very different images. They are not related at all. \"\n",
" \"Please describe the first image in one sentence, and then describe the second image in another sentence.\",\n",
" \"Please describe the first image in one sentence, and then describe the second image in another sentence.\",\n",
" },\n",
" ],\n",
" }\n",
......
docs/index.rst
View file @ 72e979bf
......@@ -25,6 +25,7 @@ The core features include:
backend/openai_api_completions.ipynb
backend/openai_api_vision.ipynb
backend/native_api.ipynb
backend/backend.md
......
docs/start/send_request.ipynb
View file @ 72e979bf
......@@ -36,55 +36,7 @@
"shell.execute_reply": "2024-11-01T02:46:42.809147Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-11-02 00:27:25.383621: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:479] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"2024-11-02 00:27:25.396224: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:10575] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"2024-11-02 00:27:25.396257: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1442] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"2024-11-02 00:27:25.922262: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
"[2024-11-02 00:27:34] server_args=ServerArgs(model_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='meta-llama/Meta-Llama-3.1-8B-Instruct', chat_template=None, is_embedding=False, host='0.0.0.0', port=30000, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=259802610, constrained_json_whitespace_pattern=None, decode_log_interval=40, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n",
"[2024-11-02 00:27:43 TP0] Init torch distributed begin.\n",
"[2024-11-02 00:27:48 TP0] Load weight begin. avail mem=76.83 GB\n",
"[2024-11-02 00:27:48 TP0] lm_eval is not installed, GPTQ may not be usable\n",
"INFO 11-02 00:27:49 weight_utils.py:243] Using model weights format ['*.safetensors']\n",
"Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]\n",
"Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:01<00:05, 1.77s/it]\n",
"Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:03<00:03, 1.78s/it]\n",
"Loading safetensors checkpoint shards: 75% Completed | 3/4 [00:05<00:01, 1.77s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:05<00:00, 1.27s/it]\n",
"Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:05<00:00, 1.46s/it]\n",
"\n",
"[2024-11-02 00:27:55 TP0] Load weight end. type=LlamaForCausalLM, dtype=torch.bfloat16, avail mem=61.82 GB\n",
"[2024-11-02 00:27:55 TP0] Memory pool end. avail mem=8.19 GB\n",
"[2024-11-02 00:27:56 TP0] Capture cuda graph begin. This can take up to several minutes.\n",
"[2024-11-02 00:28:05 TP0] max_total_num_tokens=430915, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n",
"[2024-11-02 00:28:05] INFO: Started server process [109933]\n",
"[2024-11-02 00:28:05] INFO: Waiting for application startup.\n",
"[2024-11-02 00:28:05] INFO: Application startup complete.\n",
"[2024-11-02 00:28:05] INFO: Uvicorn running on http://0.0.0.0:30000 (Press CTRL+C to quit)\n",
"[2024-11-02 00:28:06] INFO: 127.0.0.1:59502 - \"GET /v1/models HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:28:06] INFO: 127.0.0.1:59516 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:28:06 TP0] Prefill batch. #new-seq: 1, #new-token: 7, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:28:06] INFO: 127.0.0.1:59522 - \"POST /generate HTTP/1.1\" 200 OK\n",
"[2024-11-02 00:28:06] The server is fired up and ready to roll!\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'><br><br> NOTE: Typically, the server runs in a separate terminal.<br> In this notebook, we run the server and notebook code together, so their outputs are combined.<br> To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.<br> </strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
......@@ -123,45 +75,7 @@
"shell.execute_reply": "2024-11-01T02:46:51.435965Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n",
"100 278 0 0 100 278 0 1387 --:--:-- --:--:-- --:--:-- 1383"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:28:48 TP0] Prefill batch. #new-seq: 1, #new-token: 11, #cached-token: 42, cache hit rate: 40.19%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:28:48 TP0] Decode batch. #running-req: 1, #token: 75, token usage: 0.00, gen throughput (token/s): 1.46, #queue-req: 0\n",
"[2024-11-02 00:28:49] INFO: 127.0.0.1:53714 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100 871 100 593 100 278 1788 838 --:--:-- --:--:-- --:--:-- 2623\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>{\"id\":\"a0714277fab546c5b6d91724aa3e27a3\",\"object\":\"chat.completion\",\"created\":1730507329,\"model\":\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"An LLM, or Large Language Model, is a type of artificial intelligence (AI) designed to process and generate human-like language, often used in applications such as chatbots, virtual assistants, and language translation software.\"},\"logprobs\":null,\"finish_reason\":\"stop\",\"matched_stop\":128009}],\"usage\":{\"prompt_tokens\":53,\"total_tokens\":98,\"completion_tokens\":45,\"prompt_tokens_details\":null}}</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import subprocess\n",
"\n",
......@@ -209,29 +123,7 @@
"shell.execute_reply": "2024-11-01T02:46:52.895318Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:03:52 TP0] Prefill batch. #new-seq: 1, #new-token: 20, #cached-token: 29, cache hit rate: 29.13%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:03:52 TP0] Decode batch. #running-req: 1, #token: 65, token usage: 0.00, gen throughput (token/s): 11.33, #queue-req: 0\n",
"[2024-11-02 00:03:53] INFO: 127.0.0.1:57008 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>ChatCompletion(id='a6590143c40f4732a5c57d4c91b43f05', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='Here are 3 countries and their capitals:\\n\\n1. **Country:** Japan\\n**Capital:** Tokyo\\n\\n2. **Country:** Australia\\n**Capital:** Canberra\\n\\n3. **Country:** Brazil\\n**Capital:** Brasília', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=None), matched_stop=128009)], created=1730505833, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=46, prompt_tokens=49, total_tokens=95, completion_tokens_details=None, prompt_tokens_details=None))</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import openai\n",
"\n",
......@@ -264,29 +156,7 @@
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-11-02 00:05:04 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 5, cache hit rate: 33.04%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
"[2024-11-02 00:05:04 TP0] Decode batch. #running-req: 1, #token: 26, token usage: 0.00, gen throughput (token/s): 3.10, #queue-req: 0\n",
"[2024-11-02 00:05:04] INFO: 127.0.0.1:60536 - \"POST /generate HTTP/1.1\" 200 OK\n"
]
},
{
"data": {
"text/html": [
"<strong style='color: #00008B;'>{'text': ' a city of romance, art, fashion, and history. Paris is a must-visit destination for anyone who loves culture, architecture, and cuisine. From the', 'meta_info': {'prompt_tokens': 6, 'completion_tokens': 32, 'completion_tokens_wo_jump_forward': 32, 'cached_tokens': 5, 'finish_reason': {'type': 'length', 'length': 32}, 'id': 'd882513c180d4c5981488257ccab4b9f'}, 'index': 0}</strong>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"import requests\n",
"\n",
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment