Skip to content

[CI] Use real vLLM ModelConfig object in init_device test #937

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

Merged
merged 1 commit into from
Oct 24, 2025
Merged

[CI] Use real vLLM ModelConfig object in init_device test #937

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
6 changes: 2 additions & 4 deletions tests/worker/tpu_worker_jax_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from unittest.mock import MagicMock, patch

import pytest
from vllm.config import ModelConfig
from vllm.lora.request import LoRARequest
from vllm.v1.kv_cache_interface import KVCacheConfig
from vllm.v1.outputs import DraftTokenIds
Expand All @@ -27,9 +28,6 @@ def mock_vllm_config():
This version builds the mock explicitly to avoid spec-related AttributeErrors.
"""
# Create mocks for the nested config objects first
mock_model_conf = MagicMock()
mock_model_conf.trust_remote_code = False

mock_cache_conf = MagicMock()
mock_cache_conf.gpu_memory_utilization = 0.9
mock_cache_conf.num_gpu_blocks = 0
Expand All @@ -43,7 +41,7 @@ def mock_vllm_config():

# Create the main config mock and attach the others without a top-level spec
config = MagicMock()
config.model_config = mock_model_conf
config.model_config = ModelConfig(model="Qwen/Qwen3-0.6B")
config.cache_config = mock_cache_conf
config.parallel_config = mock_parallel_conf
config.additional_config = mock_additional_config
Expand Down