[Attention] Add FlashInfer Sparse MLA backend (#33451)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

vllm/model_executor/layers/attention/mla_attention.py

@@ -334,6 +334,7 @@ class MLAAttention(nn.Module, AttentionLayerBase):
             block_size,
             use_mla=True,
             use_sparse=use_sparse,
+            num_heads=self.num_heads,
         )
 
         if (