[Frontend] Require flag for loading text and image embeds (#27204)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-22 11:52:02 -04:00
parent db6f28d898
commit 58fab50d82
25 changed files with 203 additions and 64 deletions
--- a/tests/models/multimodal/generation/test_qwen2_vl.py
+++ b/tests/models/multimodal/generation/test_qwen2_vl.py
@@ -292,6 +292,7 @@ def run_embedding_input_test(
        tensor_parallel_size=tensor_parallel_size,
        distributed_executor_backend=distributed_executor_backend,
        default_torch_num_threads=1,
+        enable_mm_embeds=True,
    ) as vllm_model:
        outputs_per_case_for_original_input = [
            vllm_model.generate_greedy_logprobs(