Skip to content

Use tempfile for GPU selection test temp paths #14

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
sonarqube-agent wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Use tempfile for GPU selection test temp paths #14

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
52ee13a
fix: Address SonarQube issue
sonarqube-agent[bot] Aug 14, 2026
d948bc5
fix: Address 5 SonarQube issues
sonarqube-agent[bot] Aug 14, 2026
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
135 changes: 75 additions & 60 deletions studio/backend/tests/test_gpu_selection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
import importlib.util
import os
import re
import tempfile
import unittest
from pathlib import Path
from types import SimpleNamespace
Expand Down Expand Up @@ -724,38 +725,41 @@ def test_inference_route_rejects_gpu_ids_for_gguf(self):
"routes/inference.py",
)
request = LoadRequest(model_path = "unsloth/test.gguf", gpu_ids = [0, 1])
model_config = SimpleNamespace(
is_gguf = True,
is_lora = False,
gguf_hf_repo = None,
gguf_file = "/tmp/test.gguf",
gguf_mmproj_file = None,
gguf_variant = None,
identifier = "unsloth/test.gguf",
display_name = "unsloth/test.gguf",
is_vision = False,
is_audio = False,
audio_type = None,
has_audio_input = False,
)

with patch.object(
inference_route.ModelConfig,
"from_identifier",
return_value = model_config,
):
with self.assertRaises(HTTPException) as exc_info:
asyncio.run(
inference_route.load_model(
request,
SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
),
current_subject = "test-user",
)
with tempfile.TemporaryDirectory() as temp_dir:
model_config = SimpleNamespace(
is_gguf = True,
is_lora = False,
gguf_hf_repo = None,
gguf_file = str(Path(temp_dir) / "test.gguf"),
gguf_mmproj_file = None,
gguf_variant = None,
identifier = "unsloth/test.gguf",
display_name = "unsloth/test.gguf",
is_vision = False,
is_audio = False,
audio_type = None,
has_audio_input = False,
)

with patch.object(
inference_route.ModelConfig,
"from_identifier",
return_value = model_config,
):
request_context = SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
)
load_model_coro = inference_route.load_model(
request,
request_context,
current_subject = "test-user",
)

with self.assertRaises(HTTPException) as exc_info:
asyncio.run(load_model_coro)

self.assertEqual(exc_info.exception.status_code, 400)
self.assertIn("GGUF", exc_info.exception.detail)
Expand Down Expand Up @@ -794,10 +798,11 @@ def start_training(self, **kwargs):
return_value = SimpleNamespace(current_checkpoint = None),
),
):
training_task = training_route.start_training(
request, current_subject = "test-user"
)
with self.assertRaises(HTTPException) as exc_info:
asyncio.run(
training_route.start_training(request, current_subject = "test-user")
)
asyncio.run(training_task)

self.assertEqual(exc_info.exception.status_code, 400)
self.assertIn("gpu_ids [99]", exc_info.exception.detail)
Expand Down Expand Up @@ -825,6 +830,8 @@ def start_training(self, **kwargs):
"Invalid gpu_ids [1]: explicit physical GPU IDs are unsupported when CUDA_VISIBLE_DEVICES uses UUID/MIG entries"
)

coroutine = training_route.start_training(request, current_subject = "test-user")

with (
patch.object(
training_route, "get_training_backend", return_value = DummyBackend()
Expand All @@ -839,9 +846,7 @@ def start_training(self, **kwargs):
),
):
with self.assertRaises(HTTPException) as exc_info:
asyncio.run(
training_route.start_training(request, current_subject = "test-user")
)
asyncio.run(coroutine)

self.assertEqual(exc_info.exception.status_code, 400)
self.assertIn("UUID/MIG", exc_info.exception.detail)
Expand Down Expand Up @@ -871,6 +876,22 @@ class DummyInferenceBackend:
def load_model(self, **kwargs):
raise ValueError("Invalid gpu_ids [99]")

route_request = SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
)

async def load_model_call():
await inference_route.load_model(
request,
route_request,
current_subject = "test-user",
)

def run_load_model_call():
asyncio.run(load_model_call())

with (
patch.object(
inference_route.ModelConfig,
Expand All @@ -892,18 +913,7 @@ def load_model(self, **kwargs):
return_value = SimpleNamespace(current_checkpoint = None),
),
):
with self.assertRaises(HTTPException) as exc_info:
asyncio.run(
inference_route.load_model(
request,
SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
),
current_subject = "test-user",
)
)
exc_info = self.assertRaises(HTTPException, run_load_model_call)

self.assertEqual(exc_info.exception.status_code, 400)
self.assertIn("gpu_ids [99]", exc_info.exception.detail)
Expand Down Expand Up @@ -935,6 +945,22 @@ def load_model(self, **kwargs):
"Invalid gpu_ids [1]: explicit physical GPU IDs are unsupported when CUDA_VISIBLE_DEVICES uses UUID/MIG entries"
)

route_request = SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
)

async def load_model_call():
await inference_route.load_model(
request,
route_request,
current_subject = "test-user",
)

def run_load_model_call():
asyncio.run(load_model_call())

with (
patch.object(
inference_route.ModelConfig,
Expand All @@ -956,18 +982,7 @@ def load_model(self, **kwargs):
return_value = SimpleNamespace(current_checkpoint = None),
),
):
with self.assertRaises(HTTPException) as exc_info:
asyncio.run(
inference_route.load_model(
request,
SimpleNamespace(
app = SimpleNamespace(
state = SimpleNamespace(llama_parallel_slots = 1),
),
),
current_subject = "test-user",
)
)
exc_info = self.assertRaises(HTTPException, run_load_model_call)

self.assertEqual(exc_info.exception.status_code, 400)
self.assertIn("UUID/MIG", exc_info.exception.detail)
Expand Down