[Misc][Docs] Raise error when flashinfer is not installed and VLLM_ATTENTION_BACKEND is set (#12513)

Signed-off-by: NickLucche <nlucches@redhat.com>

docs/source/getting_started/quickstart.md

@@ -184,3 +184,13 @@ chat_response = client.chat.completions.create(
 )
 print("Chat response:", chat_response)
 ```
+
+## On Attention Backends
+
+Currently, vLLM supports multiple backends for efficient Attention computation across different platforms and accelerator architectures. It automatically selects the most performant backend compatible with your system and model specifications.
+
+If desired, you can also manually set the backend of your choice by configuring the environment variable `VLLM_ATTENTION_BACKEND` to one of the following options: `FLASH_ATTN`, `FLASHINFER` or `XFORMERS`.
+
+```{attention}
+There are no pre-built vllm wheels containing Flash Infer, so you must install it in your environment first. Refer to the [Flash Infer official docs](https://docs.flashinfer.ai/) or see [Dockerfile](https://github.com/vllm-project/vllm/blob/main/Dockerfile) for instructions on how to install it.
+```

vllm/config.py

@@ -9,6 +9,7 @@ import sys
 import warnings
 from contextlib import contextmanager
 from dataclasses import dataclass, field, replace
+from importlib.util import find_spec
 from pathlib import Path
 from typing import (TYPE_CHECKING, Any, Callable, ClassVar, Counter, Dict,
                     Final, List, Literal, Mapping, Optional, Protocol, Set,
@@ -294,6 +295,14 @@ class ModelConfig:
 
         self.maybe_pull_model_tokenizer_for_s3(model, 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/Dockerfile"
+                "for instructions on how to install it.")
+
         # The tokenizer version is consistent with the model version by default.
         if tokenizer_revision is None:
             self.tokenizer_revision = revision