mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-12 12:54:52 +00:00
add docker load_tests
This commit is contained in:
parent
7830de1566
commit
cd1e2cd2cf
@ -36,7 +36,7 @@ export function get_options() {
|
|||||||
load_test: {
|
load_test: {
|
||||||
executor: 'constant-arrival-rate',
|
executor: 'constant-arrival-rate',
|
||||||
duration: '60s',
|
duration: '60s',
|
||||||
preAllocatedVUs: 100,
|
preAllocatedVUs: 50, // not enough RAM for 100 VUs
|
||||||
rate: 1,
|
rate: 1,
|
||||||
timeUnit: '1s',
|
timeUnit: '1s',
|
||||||
},
|
},
|
||||||
@ -68,13 +68,16 @@ export default function run() {
|
|||||||
const headers = { 'Content-Type': 'application/json' };
|
const headers = { 'Content-Type': 'application/json' };
|
||||||
const query = shareGPT[scenario.iterationInTest % shareGPT.length];
|
const query = shareGPT[scenario.iterationInTest % shareGPT.length];
|
||||||
const payload = JSON.stringify(generate_payload(query, max_new_tokens));
|
const payload = JSON.stringify(generate_payload(query, max_new_tokens));
|
||||||
const res = http.post(`http://${host}/v1/chat/completions`, payload, {
|
const res = http.post(`https://${host}/v1/chat/completions`, payload, {
|
||||||
headers,
|
headers,
|
||||||
});
|
});
|
||||||
if (res.status >= 400 && res.status < 500) {
|
if (res.status >= 400 && res.status < 500) {
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if (res.status !== 200) {
|
||||||
|
console.error(res.body);
|
||||||
|
}
|
||||||
|
|
||||||
check(res, {
|
check(res, {
|
||||||
'Post status is 200': (res) => res.status === 200,
|
'Post status is 200': (res) => res.status === 200,
|
||||||
|
12
load_tests/docker-compose.yml
Normal file
12
load_tests/docker-compose.yml
Normal file
@ -0,0 +1,12 @@
|
|||||||
|
services:
|
||||||
|
|
||||||
|
# How to run:
|
||||||
|
# HOST=..... docker compose up
|
||||||
|
tgi_load_test:
|
||||||
|
image: grafana/k6
|
||||||
|
command: run /load_tests/common.js
|
||||||
|
environment:
|
||||||
|
- HOST=${HOST}
|
||||||
|
- MODEL_ID=${MODEL_ID}
|
||||||
|
volumes:
|
||||||
|
- ./:/load_tests:Z
|
Loading…
Reference in New Issue
Block a user