misc: update REAMDME.md (#1003)

Author: yzh119

README.md

@@ -48,15 +48,15 @@ Using our PyTorch API is the easiest way to get started:
 We provide prebuilt python wheels for Linux. Install FlashInfer with the following command:
 
 ```bash
-# For CUDA 12.4 & torch 2.5
-pip install flashinfer-python -i https://flashinfer.ai/whl/cu124/torch2.5
+# For CUDA 12.6 & torch 2.6
+pip install flashinfer-python -i https://flashinfer.ai/whl/cu126/torch2.6
 # For other CUDA & torch versions, check https://docs.flashinfer.ai/installation.html
 ```
 
 To try the latest features from the main branch, use our nightly-built wheels:
 
 ```bash
-pip install flashinfer-python -i https://flashinfer.ai/whl/nightly/cu124/torch2.4
+pip install flashinfer-python -i https://flashinfer.ai/whl/nightly/cu126/torch2.6
 ```
 
 For a JIT version (compiling every kernel from scratch, [NVCC](https://developer.nvidia.com/cuda-downloads) is required), install from [PyPI](https://pypi.org/project/flashinfer-python/):

docs/installation.rst

@@ -27,6 +27,21 @@ Quick Start
 The easiest way to install FlashInfer is via pip, we host wheels with indexed URL for different PyTorch versions and CUDA versions. Please note that the package currently used by FlashInfer is named ``flashinfer-python``, not ``flashinfer``.
 
 .. tabs::
+    .. tab:: PyTorch 2.6
+
+        .. tabs::
+
+            .. tab:: CUDA 12.6
+
+                .. code-block:: bash
+
+                    pip install flashinfer-python -i https://flashinfer.ai/whl/cu126/torch2.6/
+
+            .. tab:: CUDA 12.4
+
+                .. code-block:: bash
+
+                    pip install flashinfer-python -i https://flashinfer.ai/whl/cu124/torch2.6/
 
     .. tab:: PyTorch 2.5