Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add docker load_tests #2387

Closed
wants to merge 5 commits into from
Closed

add docker load_tests #2387

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
cd1e2cd
add docker load_tests
ngxson Aug 9, 2024
b727e0a
only 10 VUs
ngxson Aug 12, 2024
d5d168a
test throughput
ngxson Aug 12, 2024
a6506a5
update
ngxson Aug 14, 2024
9c83e04
limit nb input tokens
ngxson Aug 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions load_tests/common.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ export function get_options() {
load_test: {
executor: 'constant-arrival-rate',
duration: '60s',
preAllocatedVUs: 100,
preAllocatedVUs: 10, // not enough RAM for 100 VUs
rate: 1,
timeUnit: '1s',
},
Expand Down Expand Up @@ -68,13 +68,16 @@ export default function run() {
const headers = { 'Content-Type': 'application/json' };
const query = shareGPT[scenario.iterationInTest % shareGPT.length];
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,
});
if (res.status >= 400 && res.status < 500) {
return;
}

if (res.status !== 200) {
console.error(res.body);
}

check(res, {
'Post status is 200': (res) => res.status === 200,
Expand Down
12 changes: 12 additions & 0 deletions load_tests/docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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