[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

vllm/config/model.py

@@ -4,7 +4,6 @@
 import warnings
 from collections.abc import Callable
 from dataclasses import InitVar, field
-from importlib.util import find_spec
 from typing import TYPE_CHECKING, Any, Literal, cast, get_args
 
 import torch
@@ -467,18 +466,6 @@ class ModelConfig:
 
         self.maybe_pull_model_tokenizer_for_runai(self.model, self.tokenizer)
 
-        if (
-            (backend := envs.VLLM_ATTENTION_BACKEND)
-            and backend == "FLASHINFER"
-            and find_spec("flashinfer") is None
-        ):
-            raise ValueError(
-                "VLLM_ATTENTION_BACKEND is set to FLASHINFER, but flashinfer "
-                "module was not found. See "
-                "https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile "  # noqa: E501
-                "for instructions on how to install it."
-            )
-
         from vllm.platforms import current_platform
 
         if self.override_attention_dtype is not None and not current_platform.is_rocm():