[Kernel] Add KernelConfig flag to enable/disable FlashInfer autotune (#34006)

Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

vllm/config/kernel.py

@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from collections.abc import Callable
+from typing import Any
+
+from pydantic import Field, field_validator
+
+from vllm.config.utils import config
+from vllm.utils.hashing import safe_hash
+
+
+@config
+class KernelConfig:
+    """Configuration for kernel selection and warmup behavior."""
+
+    enable_flashinfer_autotune: bool = Field(default=None)
+    """If True, run FlashInfer autotuning during kernel warmup."""
+
+    def compute_hash(self) -> str:
+        """
+        WARNING: Whenever a new field is added to this config,
+        ensure that it is included in the factors list if
+        it affects the computation graph.
+
+        Provide a hash that uniquely identifies all the configs
+        that affect the structure of the computation
+        graph from input ids/embeddings to the final hidden states,
+        excluding anything before input ids/embeddings and after
+        the final hidden states.
+        """
+        # no factors to consider.
+        # this config will not affect the computation graph.
+        factors: list[Any] = []
+        hash_str = safe_hash(str(factors).encode(), usedforsecurity=False).hexdigest()
+        return hash_str
+
+    @field_validator("enable_flashinfer_autotune", mode="wrap")
+    @classmethod
+    def _skip_none_validation(cls, value: Any, handler: Callable) -> Any:
+        """Skip validation if the value is `None` when initialization is delayed."""
+        if value is None:
+            return value
+        return handler(value)