diff --git a/.github/scripts/fbgemm_gpu_test.bash b/.github/scripts/fbgemm_gpu_test.bash
index 358f4c120..0bd83f73a 100644
--- a/.github/scripts/fbgemm_gpu_test.bash
+++ b/.github/scripts/fbgemm_gpu_test.bash
@@ -508,8 +508,8 @@ test_fbgemm_gpu_setup_and_pip_install () {
     )
   elif [ "$variant_type" == "rocm" ]; then
     local variant_versions=(
-      6.1.2
       6.2.4
+      6.3
     )
   elif [ "$variant_type" == "cpu" ]; then
     local variant_versions=(
diff --git a/fbgemm_gpu/docs/src/fbgemm_gpu-development/BuildInstructions.rst b/fbgemm_gpu/docs/src/fbgemm_gpu-development/BuildInstructions.rst
index 383ea0533..71b116796 100644
--- a/fbgemm_gpu/docs/src/fbgemm_gpu-development/BuildInstructions.rst
+++ b/fbgemm_gpu/docs/src/fbgemm_gpu-development/BuildInstructions.rst
@@ -158,6 +158,12 @@ module.  CUTLASS should be already be available in the repository as a git
 submodule (see :ref:`fbgemm-gpu.build.prepare`).  The following include paths
 are already added to the CMake configuration:
 
+.. code:: cmake
+  set(THIRDPARTY ${FBGEMM}/external)
+
+  ${THIRDPARTY}/cutlass/include
+  ${THIRDPARTY}/cutlass/tools/util/include
+
 
 Set Up for ROCm Build
 ---------------------
@@ -207,7 +213,7 @@ guide <https://rocm.docs.amd.com/en/latest/>`__:
   apt update
 
   # Download the installer
-  wget -q https://repo.radeon.com/amdgpu-install/5.6.1/ubuntu/focal/amdgpu-install_5.6.50601-1_all.deb -O amdgpu-install.deb
+  wget -q https://repo.radeon.com/amdgpu-install/6.3.1/ubuntu/focal/amdgpu-install_6.3.60301-1_all.deb -O amdgpu-install.deb
 
   # Run the installer
   apt install ./amdgpu-install.deb
@@ -397,7 +403,7 @@ more deterministic and thus reliable:
   conda run -n ${env_name} pip install --pre torch --index-url https://download.pytorch.org/whl/test/cu126/
 
   # Install a specific version, CUDA variant
-  conda run -n ${env_name} pip install torch==2.1.0+cu121 --index-url https://download.pytorch.org/whl/cu126/
+  conda run -n ${env_name} pip install torch==2.6.0+cu126 --index-url https://download.pytorch.org/whl/cu126/
 
   # Install the latest nightly, ROCm variant
   conda run -n ${env_name} pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/rocm6.3/
diff --git a/fbgemm_gpu/docs/src/fbgemm_gpu-development/InstallationInstructions.rst b/fbgemm_gpu/docs/src/fbgemm_gpu-development/InstallationInstructions.rst
index 30f1a3641..91f06c664 100644
--- a/fbgemm_gpu/docs/src/fbgemm_gpu-development/InstallationInstructions.rst
+++ b/fbgemm_gpu/docs/src/fbgemm_gpu-development/InstallationInstructions.rst
@@ -50,7 +50,11 @@ Note that the list of supported CUDA and ROCm architectures refer to the targets
 support available in the default installation packages, and that building for
 other architecures may be possible, but not guaranteed.
 
-For more information, please visit the `FBGEMM Releases Page <https://github.com/pytorch/FBGEMM/releases>`__.
+For more information, please visit:
+
+- `FBGEMM Releases Page <https://github.com/pytorch/FBGEMM/releases>`_
+- `CUDA Architectures <https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/>`_
+- `ROCm Architectures <https://rocm.docs.amd.com/en/latest/reference/gpu-arch-specs.html>`_
 
 
 Set Up CPU-Only Environment
@@ -249,16 +253,16 @@ PyTorch PIP is the preferred channel for installing FBGEMM_GPU:
   pip install fbgemm-gpu --index-url https://download.pytorch.org/whl/cpu/
 
   # CUDA Nightly
-  pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121/
-  pip install --pre fbgemm-gpu --index-url https://download.pytorch.org/whl/nightly/cu121/
+  pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu126/
+  pip install --pre fbgemm-gpu --index-url https://download.pytorch.org/whl/nightly/cu126/
 
   # CUDA Release
-  pip install torch --index-url https://download.pytorch.org/whl/cu121/
-  pip install fbgemm-gpu --index-url https://download.pytorch.org/whl/cu121/
+  pip install torch --index-url https://download.pytorch.org/whl/cu126/
+  pip install fbgemm-gpu --index-url https://download.pytorch.org/whl/cu126/
 
   # ROCm Nightly
-  pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/rocm5.6/
-  pip install --pre fbgemm-gpu --index-url https://download.pytorch.org/whl/nightly/rocm5.6/
+  pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/rocm6.3/
+  pip install --pre fbgemm-gpu --index-url https://download.pytorch.org/whl/nightly/rocm6.3/
 
   # Test the installation
   python -c "import torch; import fbgemm_gpu"
diff --git a/fbgemm_gpu/experimental/gen_ai/README.md b/fbgemm_gpu/experimental/gen_ai/README.md
index 414ac14f3..8203dd4bd 100644
--- a/fbgemm_gpu/experimental/gen_ai/README.md
+++ b/fbgemm_gpu/experimental/gen_ai/README.md
@@ -39,11 +39,11 @@ y = torch.ops.fbgemm.f8f8bf16_rowwise(
 
 ```bash
 # Full FBGEMM library
-pip install fbgemm-gpu==0.8.0
-pip install fbgemm-gpu==0.8.0 --index-url https://download.pytorch.org/whl/cu121
+pip install fbgemm-gpu==1.1.0
+pip install fbgemm-gpu==1.1.0 --index-url https://download.pytorch.org/whl/cu126
+
 # FBGEMM library with GenAI operator only
 pip install fbgemm-gpu-genai
-pip install fbgemm-gpu-genai --index-url https://download.pytorch.org/whl/cu121
 ```
 
 # 2. **External Coverage**