Fix doc typo (#357)

Author: Ying1123

README.md

@@ -38,8 +38,8 @@ Using our PyTorch API is the easiest way to get started:
 We provide prebuilt wheels for Linux and you can try out FlashInfer with the following command:
 
 ```bash
-# For CUDA 12.1 & torch 2.2
-pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.2
+# For CUDA 12.1 & torch 2.3
+pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
 # For other CUDA & torch versions, please check https://docs.flashinfer.ai/installation.html
 ```
 

python/flashinfer/prefill.py

@@ -538,7 +538,7 @@ def __init__(
         custom_mask_buf: Optional[torch.Tensor] = None,
         qk_indptr_buf: Optional[torch.Tensor] = None,
     ):
-        r"""Constructor of :class:`BatchDecodeWithPagedKVCacheWrapper`.
+        r"""Constructor of :class:`BatchPrefillWithPagedKVCacheWrapper`.
 
         Parameters
         ----------
@@ -1134,7 +1134,7 @@ def __init__(
         custom_mask_buf: Optional[torch.Tensor] = None,
         qk_indptr_buf: Optional[torch.Tensor] = None,
     ):
-        r"""Constructor of :class:`BatchDecodeWithRaggedKVCacheWrapper`.
+        r"""Constructor of :class:`BatchPrefillWithRaggedKVCacheWrapper`.
 
         Parameters
         ----------