huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 16:32:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(neuron): no error anymore when requesting too many tokens

Browse Source
This commit is contained in:
David Corvoysier 2025-02-20 17:26:56 +00:00
parent 4c0fa92cb4
commit 10b57727c2
1 changed files with 0 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
integration-tests/neuron/integration/test_implicit_env.py
View File

@ -53,17 +53,6 @@ async def test_model_single_request(tgi_service):
)
assert response.details.generated_tokens == 17
# check error
try:
await tgi_service.client.text_generation("What is Deep Learning?", max_new_tokens=170000)
except ValidationError:
pass
else:
raise AssertionError(
"The previous text generation request should have failed, "
"because too many tokens were requested, it succeeded"
)
# Sampling
await tgi_service.client.text_generation(
"What is Deep Learning?",