update doc

Author: AooooooA-C

docs/source/getting-started/quickstart_vllm.md

@@ -149,7 +149,7 @@ You may directly edit the example file at `unified-cache-management/examples/ucm
 
 ### Feature 2:  Sparsity
 
-The sparse module was not compiled by default. To enable it, set the environment variable `export ENABLE_SPARSE=TRUE` and re-compile the code you built. And uncomment `ucm_sparse_config` code block in `unified-cache-management/examples/ucm_config_example.yaml`.
+The sparse module was not compiled by default. To enable it, set the environment variable `export ENABLE_SPARSE=TRUE` and re-compile the code you built. And uncomment `ucm_sparse_config` code block in `unified-cache-management/examples/ucm_config_example.yaml`. Additionally, if you want to run GSAOnDevice, you also need to set the environment variable `export VLLM_HASH_ATTENTION=1`.
 
 ## Step 3: Launching Inference
 

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

@@ -30,8 +30,8 @@ load_only_first_rank: false
 #     retrieval_stride: 5
   # Or for GSA:
   # GSA: {}
-  # Or for KvCompOnDevice:
-  # KvCompOnDevice: {}
+  # Or for GSAOnDevice:
+  # GSAOnDevice: {}
 
 
 # Whether to use layerwise loading/saving (optional, default: True for UCMConnector)