Skip to content

fix(testing): Fix Kyutai Speech-To-Text, LLaVA-OneVision, and LongCatFlash test failures on main CI #44695

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

Open
harshaljanjani wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −9
Open

fix(testing): Fix Kyutai Speech-To-Text, LLaVA-OneVision, and LongCatFlash test failures on main CI #44695

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions tests/models/kyutai_speech_to_text/test_modeling_kyutai_speech_to_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -637,7 +637,7 @@ def test_generation(self):

samples = self._load_datasamples(1)
inputs = processor(
samples,
audio=samples,
).to(torch_device)

out = model.generate(**inputs)
Expand Down Expand Up @@ -667,7 +667,7 @@ def test_generation_batched(self):

samples = self._load_datasamples(4)
inputs = processor(
samples,
audio=samples,
).to(torch_device)

out = model.generate(**inputs)
Expand Down
5 changes: 0 additions & 5 deletions tests/models/llava_onevision/test_processing_llava_onevision.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,13 +59,8 @@ def setUpClass(cls):
except Exception:
local_tiny_video = None

local_videos = [
os.path.join(repo_root, "Big_Buck_Bunny_720_10s_10MB.mp4"),
os.path.join(repo_root, "sample_demo_1.mp4"),
]
cls.local_tiny_video = local_tiny_video
MODALITY_INPUT_DATA["images"] = [local_image, local_image]
MODALITY_INPUT_DATA["videos"] = local_videos

# Force video decoding to use torchvision backend to avoid torchcodec dependency during tests
video_processing_utils.is_torchcodec_available = lambda: False # type: ignore
Expand Down
4 changes: 2 additions & 2 deletions tests/models/longcat_flash/test_modeling_longcat_flash.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,7 +352,7 @@ def test_shortcat_generation(self):
).to(self.model.device)

with torch.no_grad():
outputs = self.model.generate(inputs, max_new_tokens=10, do_sample=False)
outputs = self.model.generate(inputs["input_ids"], max_new_tokens=10, do_sample=False)

response = self.tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
expected_output = "[Round 0] USER:Paris is... ASSISTANT: dig年车龄juanaheast稍achaotingupebarebones"
Expand All @@ -370,7 +370,7 @@ def test_longcat_generation_cpu(self):
inputs = tokenizer.apply_chat_template(chat, tokenize=True, add_generation_prompt=True, return_tensors="pt")

with torch.no_grad():
outputs = model.generate(inputs, max_new_tokens=3, do_sample=False)
outputs = model.generate(inputs["input_ids"], max_new_tokens=3, do_sample=False)

response = tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
expected_output = "[Round 0] USER:Paris is... ASSISTANT:Paris is..."
Expand Down
Loading