[Bugfix][MLA] Change default SM100 MLA prefill backend back to TRT-LLM (#38562)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
(cherry picked from commit 2c734ed0e06a48808522fe8f59f6b4ffe0cf0397)

vllm/config/attention.py

@@ -30,7 +30,7 @@ class AttentionConfig:
     use_cudnn_prefill: bool = False
     """Whether to use cudnn prefill."""
 
-    use_trtllm_ragged_deepseek_prefill: bool = False
+    use_trtllm_ragged_deepseek_prefill: bool = True
     """Whether to use TRTLLM ragged deepseek prefill."""
 
     use_trtllm_attention: bool | None = None