使用兼容Triton接口
本章节以Token推理接口、文本推理接口和流式推理接口为例介绍接口调用，其他接口的调用方法请参见兼容Triton接口章节。
Token推理接口
接口名 |
Token推理接口 |
|---|---|
URL |
https://{服务IP地址}:{端口号}/v2/models/${MODEL_NAME}/infer |
请求类型 |
POST |
请求示例 |
curl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id": "42",
"inputs": [{
"name": "input0",
"shape": [
1,
10
],
"datatype": "UINT32",
"data": [
396, 319, 13996, 29877, 29901, 29907, 3333, 20718, 316, 23924
]
}],
"outputs": [{
"name": "output0"
}],
"parameters": {
"temperature": 0.5,
"top_k": 10,
"top_p": 0.95,
"do_sample": true,
"seed": null,
"repetition_penalty": 1.03,
"max_new_tokens": 20,
"watermark": true,
"priority": 5,
"timeout": 10
}
}' https://127.0.0.1:1025/v2/models/llama_65b/infer
|
返回示例 |
{
"id": "42",
"outputs": [
{
"name": "output0",
"shape": [
1,
20
],
"datatype": "UINT32",
"data": [
1,
396,
319,
13996,
29877,
29901,
29907,
3333,
20718,
316,
23924,
562,
2142,
1702,
425,
14015,
16060,
316,
383,
19498
]
}
]
}
|
文本推理接口
接口名 |
文本推理接口 |
|---|---|
URL |
https://{服务IP地址}:{端口号}/v2/models/${MODEL_NAME}/generate |
请求类型 |
POST |
请求示例 |
curl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id":"a123",
"text_input": "My name is Olivier and I",
"parameters": {
"details": true,
"do_sample": true,
"max_new_tokens":5,
"repetition_penalty": 1.1,
"seed": 123,
"temperature": 1,
"top_k": 10,
"top_p": 0.99,
"batch_size":100,
"typical_p": 0.5,
"watermark": false,
"perf_stat": true,
"priority": 5,
"timeout": 10
}
}' https://127.0.0.1:1025/v2/models/llama_65b/generate
|
返回示例 |
{
"id": "a123",
"model_name": "llama_65b",
"model_version": null,
"text_output": "live in Paris, France",
"details": {
"finish_reason": "length",
"generated_tokens": 5,
"first_token_cost": null,
"decode_cost": null,
"perf_stat": [
[
5735,
17
],
[
297,
8
],
[
3681,
7
],
[
29892,
7
],
[
3444,
7
]
]
}
}
|
流式推理接口
接口名 |
流式推理接口 |
|---|---|
URL |
https://{服务IP地址}:{端口号}/v2/models/${MODEL_NAME}/generate_stream |
请求类型 |
POST |
请求示例 |
curl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id":"a123",
"text_input": "My name is Olivier and I",
"parameters": {
"details": true,
"do_sample": true,
"max_new_tokens":5,
"repetition_penalty": 1.1,
"seed": 123,
"temperature": 1,
"top_k": 10,
"top_p": 0.99,
"batch_size":100,
"typical_p": 0.5,
"watermark": false,
"perf_stat": true,
"priority": 5,
"timeout": 10
}
}' https://127.0.0.1:1025/v2/models/llama_65b/generate_stream
|
返回示例 |
data:{"id":"a123","model_name":"llama_65b","model_version":null,"text_output":"live","details":{"generated_tokens":1,"first_token_cost":null,"decode_cost":null,"perf_stat":[[5735,28]],"batch_size":1,"queue_wait_time":5082},"prefill_time":28,"decode_time":null}
data:{"id":"a123","model_name":"llama_65b","model_version":null,"text_output":" in","details":{"generated_tokens":2,"first_token_cost":null,"decode_cost":null,"perf_stat":[[5735,28],[297,9]],"batch_size":1,"queue_wait_time":36},"prefill_time":null,"decode_time":9}
data:{"id":"a123","model_name":"llama_65b","model_version":null,"text_output":" Paris","details":{"generated_tokens":3,"first_token_cost":null,"decode_cost":null,"perf_stat":[[5735,28],[297,9],[3681,8]],"batch_size":1,"queue_wait_time":30},"prefill_time":null,"decode_time":8}
data:{"id":"a123","model_name":"llama_65b","model_version":null,"text_output":",","details":{"generated_tokens":4,"first_token_cost":null,"decode_cost":null,"perf_stat":[[5735,28],[297,9],[3681,8],[29892,7]],"batch_size":1,"queue_wait_time":23},"prefill_time":null,"decode_time":7}
data:{"id":"a123","model_name":"llama_65b","model_version":null,"text_output":" France","details":{"finish_reason":"length","generated_tokens":5,"first_token_cost":null,"decode_cost":null,"perf_stat":[[5735,28],[297,9],[3681,8],[29892,7],[3444,7]],"batch_size":1,"queue_wait_time":24},"prefill_time":null,"decode_time":7}
|
父主题： 服务化接口调用