[Core] Rework dtype resolution (#18751)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-06-01 11:04:23 +08:00
parent 1bc86a3da1
commit 6aa8f9a4e7
13 changed files with 314 additions and 119 deletions
--- a/tests/models/multimodal/generation/test_whisper.py
+++ b/tests/models/multimodal/generation/test_whisper.py
@@ -100,6 +100,7 @@ def run_test(

    with vllm_runner(
            model,
+            dtype="half",
            max_model_len=448,
            tensor_parallel_size=tensor_parallel_size,
            distributed_executor_backend=distributed_executor_backend,