[Feat] Update sparse method patches for vllm 0.11.0 (#638)

<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ OUR OFFICIAL WEBSITE.

-->

# Purpose

Update sparse method patches to adapt to vLLM 0.11.0 version.
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->

# Modifications 

Apply the patches to vLLM and vLLM-Ascend using the `git apply` command.

<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

# Test
Conducted tests on gsa_on_device in the CUDA environment.

<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.

Author: AooooooA-C

docs/source/getting-started/quickstart_vllm.md

@@ -2,7 +2,7 @@
 This document describes how to install unified-cache-management with vllm on cuda platform.
 
 ## Prerequisites
-- vllm >=0.9.1, device=cuda (vllm == 0.9.2 to use the Sparse Feature)
+- vllm >=0.9.1, device=cuda (Sparse Feature is supported in vllm 0.9.2 and v0.11.0)
 
 ## Step 1: UCM Installation
 
@@ -44,6 +44,7 @@ Download the pre-built `vllm/vllm-openai:v0.9.2` docker image and build unified-
 1. Prepare vLLM Environment
 
     For the sake of environment isolation and simplicity, we recommend preparing the vLLM environment by pulling the official, pre-built vLLM Docker image.
+    > Note: v0.11.0 is newly supported (replace the tag with v0.11.0 if needed).
 
     ```bash
     docker pull vllm/vllm-openai:v0.9.2
@@ -87,6 +88,15 @@ Download the pre-built `vllm/vllm-openai:v0.9.2` docker image and build unified-
     ```
     Apply the patch that matches your development needs:
 
+    #### vLLM 0.11.0 
+
+    Note: v0.11.0 only requires the sparse attention patch.
+
+    ```bash
+    git apply unified-cache-management/ucm/integration/vllm/patch/0.11.0/vllm-adapt-sparse.patch
+    ```
+
+    #### vLLM 0.9.2 
     - Full UCM integration (recommended):
     ```bash
     git apply unified-cache-management/ucm/integration/vllm/patch/0.9.2/vllm-adapt.patch

examples/offline_inference_kvcomphbm.py …mples/offline_inference_gsa_on_device.pyexamples/offline_inference_kvcomphbm.py renamed to examples/offline_inference_gsa_on_device.py examples/offline_inference_kvcomphbm.py renamed to examples/offline_inference_gsa_on_device.py

@@ -77,7 +77,7 @@ def build_llm_with_uc(module_path: str, name: str, model: str):
                     },
                 }
             ],
-            "ucm_sparse_config": {"KvCompOnDevice": {}},
+            "ucm_sparse_config": {"GSAOnDevice": {}},
         },
     )