huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Deactivating the flaky test.

Browse Source
This commit is contained in:
Nicolas Patry 2025-01-31 12:33:08 +01:00
parent 77bc943341
commit 6a7b92a7ea
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
1 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
integration-tests/models/test_flash_starcoder_gptq.py
View File

@ -25,21 +25,23 @@ async def test_flash_starcoder_gptq(flash_starcoder_gptq, generous_response_snap
assert response == generous_response_snapshot
@pytest.mark.release
@pytest.mark.asyncio
async def test_flash_starcoder_gptq_default_params(
flash_starcoder_gptq, generous_response_snapshot
):
response = await flash_starcoder_gptq.generate(
"def geometric_mean(L: List[float]):",
max_new_tokens=20,
temperature=0.2,
top_p=0.95,
decoder_input_details=True,
seed=0,
)
assert response.details.generated_tokens == 2
assert response == generous_response_snapshot
# Deactivated because it's flaky
# Only this model seems affected and it's only a logprob precision issue.
# @pytest.mark.release
# @pytest.mark.asyncio
# async def test_flash_starcoder_gptq_default_params(
# flash_starcoder_gptq, generous_response_snapshot
# ):
# response = await flash_starcoder_gptq.generate(
# "def geometric_mean(L: List[float]):",
# max_new_tokens=20,
# temperature=0.2,
# top_p=0.95,
# decoder_input_details=True,
# seed=0,
# )
# assert response.details.generated_tokens == 2
# assert response == generous_response_snapshot
@pytest.mark.release