remove _grouped_size_compiled_for_decode_kernels (#3453)

python/sglang/srt/layers/attention/flashinfer_backend.py

@@ -1077,21 +1077,6 @@ def should_use_tensor_core(
     if env_override is not None:
         return env_override.lower() == "true"
 
-    # Try to use _grouped_size_compiled_for_decode_kernels if available
-    # This is for flashinfer <=0.1.6. Otherwise, there is an accuracy bug
-    try:
-        from flashinfer.decode import _grouped_size_compiled_for_decode_kernels
-
-        if not _grouped_size_compiled_for_decode_kernels(
-            num_attention_heads,
-            num_kv_heads,
-        ):
-            return True
-        else:
-            return False
-    except (ImportError, AttributeError):
-        pass
-
     # Calculate GQA group size
     gqa_group_size = num_attention_heads // num_kv_heads