From 80a76df479ad117dffae15ecc83adcef956aa8f4 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 15:30:08 +0200
Subject: [PATCH 01/28] Revise AMD installation guide

---
 docs/AMD-INSTALLATION.md | 191 +++++++++++++++++++++++++++------------
 1 file changed, 134 insertions(+), 57 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 4f05589eb..b12277017 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -1,44 +1,48 @@
-# Installation Guide
+# AMD Installation Guide for Windows (TheRock)
 
-This guide covers installation for specific RDNA3 and RDNA3.5 AMD CPUs (APUs) and GPUs
-running under Windows. 
+This guide covers installation for AMD GPUs and APUs running under Windows using TheRock's official PyTorch wheels.
 
-tl;dr: Radeon RX 7900 GOOD, RX 9700 BAD, RX 6800 BAD. (I know, life isn't fair).
+## Supported GPUs
 
-Currently supported (but not necessary tested):
+Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md), the following GPUs are supported on Windows:
 
-**gfx110x**:
+### **gfx110X-all** (RDNA 3):
+* AMD RX 7900 XTX (gfx1100)
+* AMD RX 7800 XT (gfx1101)
+* AMD RX 7700 XT (gfx1101)
+* AMD RX 7700S / Framework Laptop 16 (gfx1102)
+* AMD Radeon 780M Laptop iGPU (gfx1103)
 
-* Radeon RX 7600
-* Radeon RX 7700 XT
-* Radeon RX 7800 XT
-* Radeon RX 7900 GRE
-* Radeon RX 7900 XT
-* Radeon RX 7900 XTX
+### **gfx1150** (RDNA 3.5 APU) 
+* AMD Radeon 890M (Ryzen AI 9 HX 370 - Strix Point)
 
-**gfx1151**:
+### **gfx1151** (RDNA 3.5 APU):
+* AMD Strix Halo APUs
 
-* Ryzen 7000 series APUs (Phoenix)
-* Ryzen Z1 (e.g., handheld devices like the ROG Ally)
+### **gfx120X-all** (RDNA 4):
+* AMD RX 9060 XT (gfx1200)
+* AMD RX 9060 (gfx1200)
+* AMD RX 9070 XT (gfx1201)
+* AMD RX 9070 (gfx1201)
 
-**gfx1201**:
-
-* Ryzen 8000 series APUs (Strix Point) 
-* A [frame.work](https://frame.work/au/en/desktop) desktop/laptop
+### Also supported:
+* **gfx103X-dgpu**: (RDNA 2)
 
+**Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 
 ## Requirements
 
-- Python 3.11 (3.12 might work, 3.10 definately will not!)
+- Python 3.11 (recommended for Wan2GP - TheRock currently supports Python 3.11, 3.12, and 3.13).
+- Windows 10/11
 
 ## Installation Environment
 
-This installation uses PyTorch 2.7.0 because that's what currently available in
-terms of pre-compiled wheels.
+This installation uses PyTorch wheels built by TheRock.
 
 ### Installing Python
 
-Download Python 3.11 from [python.org/downloads/windows](https://www.python.org/downloads/windows/). Hit Ctrl+F and search for "3.11". Dont use this direct link: [https://www.python.org/ftp/python/3.11.9/python-3.11.9-amd64.exe](https://www.python.org/ftp/python/3.11.9/python-3.11.9-amd64.exe) -- that was an IQ test.
+Download Python 3.11 from [python.org/downloads/windows](https://www.python.org/downloads/windows/). Press Ctrl+F and search for "3.11.". 
+Alternatively, you can use this direct link: [Python 3.11.9 (64-bit)](https://www.python.org/ftp/python/3.11.9/python-3.11.9-amd64.exe).
 
 After installing, make sure `python --version` works in your terminal and returns 3.11.x
 
@@ -57,16 +61,14 @@ C:\Users\YOURNAME\AppData\Local\Programs\Python\Python311\Scripts\
 C:\Users\YOURNAME\AppData\Local\Programs\Python\Python311\
 ```
 
-If that doesnt work, scream into a bucket.
-
 ### Installing Git
 
-Get Git from [git-scm.com/downloads/win](https://git-scm.com/downloads/win). Default install is fine.
+Download Git from [git-scm.com/downloads/windows](https://git-scm.com/downloads/windows) and install it. The default installation options are fine.
 
 
-## Install (Windows, using `venv`)
+## Install (Windows, using a Python `venv`)
 
-### Step 1: Download and Set Up Environment
+### Step 1: Download and set up Wan2GP Environment
 
 ```cmd
 :: Navigate to your desired install directory
@@ -76,71 +78,146 @@ cd \your-path-to-wan2gp
 git clone https://github.com/deepbeepmeep/Wan2GP.git
 cd Wan2GP
 
-:: Create virtual environment using Python 3.10.9
+:: Create virtual environment
 python -m venv wan2gp-env
 
 :: Activate the virtual environment
 wan2gp-env\Scripts\activate
 ```
 
-### Step 2: Install PyTorch
+### Step 2: Install ROCm/PyTorch by TheRock
+
+**IMPORTANT:** Choose the correct index URL for your GPU family!
+
+#### For gfx110X-all (RX 7900 XTX, RX 7800 XT, etc.):
+
+```cmd
+pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/
+```
+
+#### For gfx120X-all (RX 9060, RX 9070, etc.):
+
+```cmd
+pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/
+```
+
+#### For gfx1151 (Strix Halo iGPU):
 
-The pre-compiled wheels you need are hosted at [scottt's rocm-TheRock releases](https://github.com/scottt/rocm-TheRock/releases). Find the heading that says:
+```cmd
+pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx1151/
+```
 
-**Pytorch wheels for gfx110x, gfx1151, and gfx1201**
+#### For gfx1150 (Radeon 890M - Strix Point):
 
-Don't click this link: [https://github.com/scottt/rocm-TheRock/releases/tag/v6.5.0rc-pytorch-gfx110x](https://github.com/scottt/rocm-TheRock/releases/tag/v6.5.0rc-pytorch-gfx110x). It's just here to check if you're skimming.
+```cmd
+pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2-staging/gfx1150/
+```
 
-Copy the links of the closest binaries to the ones in the example below (adjust if you're not running Python 3.11), then hit enter.
+#### For gfx103X-dgpu (RDNA 2):
 
 ```cmd
-pip install ^
-    https://github.com/scottt/rocm-TheRock/releases/download/v6.5.0rc-pytorch-gfx110x/torch-2.7.0a0+rocm_git3f903c3-cp311-cp311-win_amd64.whl ^
-    https://github.com/scottt/rocm-TheRock/releases/download/v6.5.0rc-pytorch-gfx110x/torchaudio-2.7.0a0+52638ef-cp311-cp311-win_amd64.whl ^
-    https://github.com/scottt/rocm-TheRock/releases/download/v6.5.0rc-pytorch-gfx110x/torchvision-0.22.0+9eb57cd-cp311-cp311-win_amd64.whl
+pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2-staging/gfx103X-dgpu/
 ```
 
-### Step 3: Install Dependencies
+This will automatically install the latest PyTorch, torchaudio, and torchvision wheels with ROCm support.
+
+### Step 3: Install Wan2GP Dependencies
 
 ```cmd
 :: Install core dependencies
 pip install -r requirements.txt
 ```
 
+### Step 4: Verify Installation
+
+```cmd
+python -c "import torch; print('PyTorch:', torch.__version__); print('ROCm available:', torch.cuda.is_available()); print('Device:', torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'No GPU')"
+```
+
+Expected output example:
+```
+PyTorch: 2.11.0+rocm7.12.0
+ROCm available: True
+Device: AMD Radeon RX 9070 XT
+```
+
 ## Attention Modes
 
-WanGP supports several attention implementations, only one of which will work for you:
+WanGP supports multiple attention implementations via [triton-windows](https://github.com/woct0rdho/triton-windows/).
+
+First, install `triton-windows` in your virtual environment.  
+If you have an older version of Triton installed, uninstall it first:
+
+```cmd
+pip uninstall triton
+pip install triton-windows
+```
 
-- **SDPA** (default): Available by default with PyTorch.  This uses the built-in aotriton accel library, so is actually pretty fast.
+### Supported attention implementations
 
-## Performance Profiles
+- **Sageattention V1** (Requires the `.post26` wheel or newer):
 
-Choose a profile based on your hardware:
+```cmd
+pip install "sageattention <2"
+```
+
+- **FlashAttention-2** (Only the Triton backend is supported): 
+```cmd
+git clone https://github.com/Dao-AILab/flash-attention.git
+cd flash-attention
+pip install ninja
+# Install FlashAttention-2 with the Triton backend enabled
+set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE && python setup.py install
+```
 
-- **Profile 3 (LowRAM_HighVRAM)**: Loads entire model in VRAM, requires 24GB VRAM for 8-bit quantized 14B model
-- **Profile 4 (LowRAM_LowVRAM)**: Default, loads model parts as needed, slower but lower VRAM requirement
+- **SDPA** (default): Available by default in PyTorch on post-RDNA3 GPUs.
 
 ## Running Wan2GP
 
-In future, you will have to do this:
+For future sessions, activate the environment:
 
 ```cmd
-cd \path-to\wan2gp
-wan2gp\Scripts\activate.bat
+cd \path-to\Wan2GP
+wan2gp-env\Scripts\activate
 python wgp.py
 ```
 
-For now, you should just be able to type `python wgp.py` (because you're already in the virtual environment)
-
 ## Troubleshooting
 
-- If you use a HIGH VRAM mode, don't be a fool.  Make sure you use VAE Tiled Decoding.
+### GPU Not Detected
+
+If `torch.cuda.is_available()` returns `False`:
+
+1. **Verify your GPU is supported** - Check the [Supported GPUs](#supported-gpus) list above
+2. **Check AMD drivers** - Ensure you have the latest AMD Adrenalin drivers installed
+3. **Verify correct index URL** - Make sure you used the right GPU family index URL
+
+### Installation Errors
+
+**"Could not find a version that satisfies the requirement":**
+- Double-check that you're using the correct `--index-url` for your GPU family. You can also try adding the `--pre` flag or replacing `/v2/` in the URL with `/v2/staging/`
+- Ensure you're using Python 3.11
+- Try adding `--pre` flag if not already present
+
+**"No matching distribution found":**
+- Your GPU architecture may not be supported
+- Check that you've activated your virtual environment
+
+### Performance Issues
+
+- **Monitor VRAM usage** - Reduce batch size if running out of memory
+- **Close GPU-intensive apps** - Discord hardware acceleration, browsers, etc.
+
+### Known Issues
+
+Windows packages are new and may be unstable!
 
-### Memory Issues
+Known issues are tracked at: https://github.com/ROCm/TheRock/issues/808
 
-- Use lower resolution or shorter videos
-- Enable quantization (default)
-- Use Profile 4 for lower VRAM usage
-- Consider using 1.3B models instead of 14B models
+## Additional Resources
 
-For more troubleshooting, see [TROUBLESHOOTING.md](TROUBLESHOOTING.md) 
+- [TheRock GitHub Repository](https://github.com/ROCm/TheRock/)
+- [TheRock Releases Documentation](https://github.com/ROCm/TheRock/blob/main/RELEASES.md)
+- [Supported GPU Architectures](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md)
+- [TheRock Roadmap](https://github.com/ROCm/TheRock/blob/main/ROADMAP.md)
+- [ROCm Documentation](https://rocm.docs.amd.com/)

From 006f2f210e69c826a155aadea42b350b9fd02bb2 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 15:43:59 +0200
Subject: [PATCH 02/28] Modify documentation for SDPA

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index b12277017..510521b8e 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -170,7 +170,7 @@ pip install ninja
 set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE && python setup.py install
 ```
 
-- **SDPA** (default): Available by default in PyTorch on post-RDNA3 GPUs.
+- **SDPA Flash**: Available by default in PyTorch on post-RDNA2 GPUs via AOTriton.
 
 ## Running Wan2GP
 

From 6b952d1b274b44e6e8632e5df8a8538a2ec579f6 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 15:46:14 +0200
Subject: [PATCH 03/28] Fix example paths and update Git installation link

---
 docs/AMD-INSTALLATION.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 510521b8e..16ff51887 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -56,14 +56,14 @@ If not, you probably need to fix your PATH. Go to:
 Example correct entries:
 
 ```cmd
-C:\Users\YOURNAME\AppData\Local\Programs\Python\Launcher\
-C:\Users\YOURNAME\AppData\Local\Programs\Python\Python311\Scripts\
-C:\Users\YOURNAME\AppData\Local\Programs\Python\Python311\
+C:\Users\<username>\AppData\Local\Programs\Python\Launcher\
+C:\Users\<username>\AppData\Local\Programs\Python\Python311\Scripts\
+C:\Users\<username>\AppData\Local\Programs\Python\Python311\
 ```
 
 ### Installing Git
 
-Download Git from [git-scm.com/downloads/windows](https://git-scm.com/downloads/windows) and install it. The default installation options are fine.
+Download Git from [git-scm.com/downloads/windows](https://git-scm.com/install/windows) and install it. The default installation options are fine.
 
 
 ## Install (Windows, using a Python `venv`)

From 38176754230a645336a8d7759301867518fb4222 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 15:50:45 +0200
Subject: [PATCH 04/28] Clarify CMD / PowerShell

---
 docs/AMD-INSTALLATION.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 16ff51887..486de7fbf 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -67,6 +67,9 @@ Download Git from [git-scm.com/downloads/windows](https://git-scm.com/install/wi
 
 
 ## Install (Windows, using a Python `venv`)
+> **Note:** This guide uses **Windows CMD**.  
+> If you are using PowerShell, some commands (like comments and activating the virtual environment) may differ.
+
 
 ### Step 1: Download and set up Wan2GP Environment
 

From 8b570ad1d9d8f8c81cb04a581c3d71c52b4b60a9 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 15:59:28 +0200
Subject: [PATCH 05/28] Update notes for CMD and Python usage

---
 docs/AMD-INSTALLATION.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 486de7fbf..724bab148 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -67,7 +67,7 @@ Download Git from [git-scm.com/downloads/windows](https://git-scm.com/install/wi
 
 
 ## Install (Windows, using a Python `venv`)
-> **Note:** This guide uses **Windows CMD**.  
+> **Note:** The following commands are intended for use in the Windows Command Prompt (CMD).  
 > If you are using PowerShell, some commands (like comments and activating the virtual environment) may differ.
 
 
@@ -88,6 +88,8 @@ python -m venv wan2gp-env
 wan2gp-env\Scripts\activate
 ```
 
+> **Note:** If you have multiple versions of Python installed, use `py -3.11` instead of `python` to ensure the correct version is used.
+
 ### Step 2: Install ROCm/PyTorch by TheRock
 
 **IMPORTANT:** Choose the correct index URL for your GPU family!

From c9835f234a4477a8a7f2d662ed353092f40f95d1 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:07:11 +0200
Subject: [PATCH 06/28] Revise Python installation instructions

---
 docs/AMD-INSTALLATION.md | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 724bab148..ec5ddba6c 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -41,10 +41,11 @@ This installation uses PyTorch wheels built by TheRock.
 
 ### Installing Python
 
-Download Python 3.11 from [python.org/downloads/windows](https://www.python.org/downloads/windows/). Press Ctrl+F and search for "3.11.". 
+Download Python 3.11 from [python.org/downloads/windows](https://www.python.org/downloads/windows/). Press Ctrl+F and search for "3.11." to find the newest version available for installation.
+
 Alternatively, you can use this direct link: [Python 3.11.9 (64-bit)](https://www.python.org/ftp/python/3.11.9/python-3.11.9-amd64.exe).
 
-After installing, make sure `python --version` works in your terminal and returns 3.11.x
+After installing, make sure `python --version` works in your terminal and returns `3.11.9`
 
 If not, you probably need to fix your PATH. Go to:
 
@@ -88,7 +89,7 @@ python -m venv wan2gp-env
 wan2gp-env\Scripts\activate
 ```
 
-> **Note:** If you have multiple versions of Python installed, use `py -3.11` instead of `python` to ensure the correct version is used.
+> **Note:** If you have multiple versions of Python installed, use `py -3.11 -m venv wan2gp-env` instead of `python -m venv wan2gp-env` to ensure the correct version is used.
 
 ### Step 2: Install ROCm/PyTorch by TheRock
 
@@ -160,7 +161,7 @@ pip install triton-windows
 
 ### Supported attention implementations
 
-- **Sageattention V1** (Requires the `.post26` wheel or newer):
+- **SageAttention V1** (Requires the `.post26` wheel or newer):
 
 ```cmd
 pip install "sageattention <2"

From d7a66d912ac950b78e2e3156e284aca05bf04261 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:10:07 +0200
Subject: [PATCH 07/28] Modify installation commands for FlashAttention-2

---
 docs/AMD-INSTALLATION.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index ec5ddba6c..e6eb357d9 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -172,7 +172,6 @@ pip install "sageattention <2"
 git clone https://github.com/Dao-AILab/flash-attention.git
 cd flash-attention
 pip install ninja
-# Install FlashAttention-2 with the Triton backend enabled
 set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE && python setup.py install
 ```
 

From ddd6e0b62a11420faf0fc1c5161a1017a2454e6f Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:22:08 +0200
Subject: [PATCH 08/28] Clarify steps to add Python to PATH

---
 docs/AMD-INSTALLATION.md | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index e6eb357d9..12bef1b55 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -47,14 +47,11 @@ Alternatively, you can use this direct link: [Python 3.11.9 (64-bit)](https://ww
 
 After installing, make sure `python --version` works in your terminal and returns `3.11.9`
 
-If not, you probably need to fix your PATH. Go to:
+If it doesn’t, you need to add Python to your PATH:
 
-* Windows + Pause/Break
-* Advanced System Settings
-* Environment Variables
-* Edit your `Path` under User Variables
-
-Example correct entries:
+* Press the Windows key, type Environment Variables, and select “Edit the system environment variables”.
+* In the System Properties window, click Environment Variables….
+* Under User variables, find Path, then click Edit → New and add the following entries (replace <username> with your Windows username):
 
 ```cmd
 C:\Users\<username>\AppData\Local\Programs\Python\Launcher\
@@ -62,6 +59,8 @@ C:\Users\<username>\AppData\Local\Programs\Python\Python311\Scripts\
 C:\Users\<username>\AppData\Local\Programs\Python\Python311\
 ```
 
+> **Note:** If Python still doesn't show the correct version after updating PATH, try signing out and signing back in to Windows to apply the changes.
+
 ### Installing Git
 
 Download Git from [git-scm.com/downloads/windows](https://git-scm.com/install/windows) and install it. The default installation options are fine.

From 5c75788d07a6321977699a8021513b46f25705bd Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:22:59 +0200
Subject: [PATCH 09/28] Fix formatting of note about GPU support

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 12bef1b55..6fdebafef 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -28,7 +28,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 ### Also supported:
 * **gfx103X-dgpu**: (RDNA 2)
 
-**Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
+> **Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 
 ## Requirements
 

From c42507c4d3865da557ab3668dc8b8639f02828b6 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:24:41 +0200
Subject: [PATCH 10/28] Fix formatting for RDNA2 support

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 6fdebafef..0776c5ed5 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -26,7 +26,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 * AMD RX 9070 (gfx1201)
 
 ### Also supported:
-* **gfx103X-dgpu**: (RDNA 2)
+**gfx103X-dgpu**: (RDNA 2)
 
 > **Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 

From 7e9daaa75d7a79d14a28ef3b5472c5af184b133d Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:30:08 +0200
Subject: [PATCH 11/28] Reorganize `Supported GPUs` section to match install
 order

---
 docs/AMD-INSTALLATION.md | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 0776c5ed5..82273356c 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -13,18 +13,18 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 * AMD RX 7700S / Framework Laptop 16 (gfx1102)
 * AMD Radeon 780M Laptop iGPU (gfx1103)
 
-### **gfx1150** (RDNA 3.5 APU) 
-* AMD Radeon 890M (Ryzen AI 9 HX 370 - Strix Point)
-
-### **gfx1151** (RDNA 3.5 APU):
-* AMD Strix Halo APUs
-
 ### **gfx120X-all** (RDNA 4):
 * AMD RX 9060 XT (gfx1200)
 * AMD RX 9060 (gfx1200)
 * AMD RX 9070 XT (gfx1201)
 * AMD RX 9070 (gfx1201)
 
+### **gfx1151** (RDNA 3.5 APU):
+* AMD Strix Halo APUs
+
+### **gfx1150** (RDNA 3.5 APU) 
+* AMD Radeon 890M (Ryzen AI 9 HX 370 - Strix Point)
+
 ### Also supported:
 **gfx103X-dgpu**: (RDNA 2)
 
@@ -49,9 +49,9 @@ After installing, make sure `python --version` works in your terminal and return
 
 If it doesn’t, you need to add Python to your PATH:
 
-* Press the Windows key, type Environment Variables, and select “Edit the system environment variables”.
-* In the System Properties window, click Environment Variables….
-* Under User variables, find Path, then click Edit → New and add the following entries (replace <username> with your Windows username):
+* Press the `Windows` key, type `Environment Variables`, and select `Edit the system environment variables`.
+* In the `System Properties` window, click `Environment Variables…`.
+* Under `User variables`, find `Path`, then click `Edit` → `New` and add the following entries (replace `<username>` with your Windows username):
 
 ```cmd
 C:\Users\<username>\AppData\Local\Programs\Python\Launcher\

From 257b2834f0577c0cfeb6e481ca59d1c6d05c627c Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:35:44 +0200
Subject: [PATCH 12/28] Update section title for installation instructions

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 82273356c..b1b04056b 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -66,7 +66,7 @@ C:\Users\<username>\AppData\Local\Programs\Python\Python311\
 Download Git from [git-scm.com/downloads/windows](https://git-scm.com/install/windows) and install it. The default installation options are fine.
 
 
-## Install (Windows, using a Python `venv`)
+## Installation Steps (Windows, using a Python `venv`)
 > **Note:** The following commands are intended for use in the Windows Command Prompt (CMD).  
 > If you are using PowerShell, some commands (like comments and activating the virtual environment) may differ.
 

From 4b7453f439be44a6888fb6629483288ed6b4cfb2 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:40:37 +0200
Subject: [PATCH 13/28] Update installation error messages and performance tips

---
 docs/AMD-INSTALLATION.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index b1b04056b..3926487c4 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -200,7 +200,7 @@ If `torch.cuda.is_available()` returns `False`:
 
 **"Could not find a version that satisfies the requirement":**
 - Double-check that you're using the correct `--index-url` for your GPU family. You can also try adding the `--pre` flag or replacing `/v2/` in the URL with `/v2/staging/`
-- Ensure you're using Python 3.11
+- Ensure you're using Python 3.11, and not 3.10
 - Try adding `--pre` flag if not already present
 
 **"No matching distribution found":**
@@ -209,12 +209,12 @@ If `torch.cuda.is_available()` returns `False`:
 
 ### Performance Issues
 
-- **Monitor VRAM usage** - Reduce batch size if running out of memory
-- **Close GPU-intensive apps** - Discord hardware acceleration, browsers, etc.
+- **Monitor VRAM usage** - Reduce batch size or resolution if running out of memory
+- **Close GPU-intensive apps** - Apps with hardware acceleration enabled (browsers, Discord etc.).
 
 ### Known Issues
 
-Windows packages are new and may be unstable!
+Windows packages are new and may be unstable.
 
 Known issues are tracked at: https://github.com/ROCm/TheRock/issues/808
 

From c231c627fde0ca9984922c9c08bdfdd2d27f9501 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:46:24 +0200
Subject: [PATCH 14/28] Clarify notes

---
 docs/AMD-INSTALLATION.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 3926487c4..9dd2965ec 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -28,6 +28,8 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 ### Also supported:
 **gfx103X-dgpu**: (RDNA 2)
 
+<br>
+
 > **Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 
 ## Requirements
@@ -178,7 +180,7 @@ set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE && python setup.py install
 
 ## Running Wan2GP
 
-For future sessions, activate the environment:
+For future sessions, activate the environment every time if it isn't already activated, then run `python wgp.py`:
 
 ```cmd
 cd \path-to\Wan2GP

From c699c9eaa69abaea4e51cc0b52a9ec17cfebd11b Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:47:55 +0200
Subject: [PATCH 15/28] Fix formatting

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 9dd2965ec..ca5d38288 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -26,7 +26,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 * AMD Radeon 890M (Ryzen AI 9 HX 370 - Strix Point)
 
 ### Also supported:
-**gfx103X-dgpu**: (RDNA 2)
+### **gfx103X-dgpu**: (RDNA 2)
 
 <br>
 

From 3e87d2636ae1a2307e169defe727ea75bbe607db Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 16:51:50 +0200
Subject: [PATCH 16/28] Update links in AMD installation documentation

---
 docs/AMD-INSTALLATION.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index ca5d38288..814cfda9e 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -223,7 +223,7 @@ Known issues are tracked at: https://github.com/ROCm/TheRock/issues/808
 ## Additional Resources
 
 - [TheRock GitHub Repository](https://github.com/ROCm/TheRock/)
-- [TheRock Releases Documentation](https://github.com/ROCm/TheRock/blob/main/RELEASES.md)
+- [Releases Documentation](https://github.com/ROCm/TheRock/blob/main/RELEASES.md)
 - [Supported GPU Architectures](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md)
-- [TheRock Roadmap](https://github.com/ROCm/TheRock/blob/main/ROADMAP.md)
+- [Roadmap](https://github.com/ROCm/TheRock/blob/main/ROADMAP.md)
 - [ROCm Documentation](https://rocm.docs.amd.com/)

From 9b7f01571c16e64afbc8304b4df2bda4fe96a0be Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 17:06:36 +0200
Subject: [PATCH 17/28] Enhance documentation with setup tips

---
 docs/AMD-INSTALLATION.md | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 814cfda9e..c815a87c8 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -188,6 +188,32 @@ wan2gp-env\Scripts\activate
 python wgp.py
 ```
 
+It is advised to set the following environment variables at the start of every new session (you can create a `.bat` file that activates your venv, sets these, then launches `wgp.py`):
+
+```cmd
+set ROCM_HOME=%ROCM_ROOT%
+set PATH=%ROCM_ROOT%\lib\llvm\bin;%ROCM_BIN%;%PATH%
+set CC=clang-cl
+set CXX=clang-cl
+set DISTUTILS_USE_SDK=1
+set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE
+set TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
+```
+
+MIOpen (AMD's cuDNN equivalent) is not yet stable; it frequently causes OOMs, crashes the display driver, and significantly increases generation times. Currently, it is recommended to use fast mode by setting `set MIOPEN_FIND_MODE=FAST`, or to disable it entirely by editing `wgp.py` and adding the following line below `import torch` (line 51):
+
+```cmd
+torch.backends.cudnn.enabled = False
+```
+
+To verify that it is disabled, or to enable verbose logging, you can set:
+
+```cmd
+set MIOPEN_ENABLE_LOGGING=1
+set MIOPEN_ENABLE_LOGGING_CMD=1
+set MIOPEN_LOG_LEVEL=5
+```
+
 ## Troubleshooting
 
 ### GPU Not Detected

From 0e5fcdcac19d94e78ef3f3b277fa7956c8fe1828 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 17:11:41 +0200
Subject: [PATCH 18/28] Add advice on setting environment variables for AMD

Added advice on setting environment variables for AMD.
---
 docs/AMD-INSTALLATION.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index c815a87c8..2a233f9a2 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -185,6 +185,7 @@ For future sessions, activate the environment every time if it isn't already act
 ```cmd
 cd \path-to\Wan2GP
 wan2gp-env\Scripts\activate
+:: Add the AMD-specific environment variables mentioned below here
 python wgp.py
 ```
 

From 366d0c20635a49427d7988e357dd0fe5a18ab71f Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 17:22:46 +0200
Subject: [PATCH 19/28] Modify installation commands

---
 docs/AMD-INSTALLATION.md | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 2a233f9a2..47dbd6a80 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -99,31 +99,31 @@ wan2gp-env\Scripts\activate
 #### For gfx110X-all (RX 7900 XTX, RX 7800 XT, etc.):
 
 ```cmd
-pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/
+pip install --pre torch torchaudio torchvision rocm[devel] --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/
 ```
 
 #### For gfx120X-all (RX 9060, RX 9070, etc.):
 
 ```cmd
-pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/
+pip install --pre torch torchaudio torchvision rocm[devel] --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/
 ```
 
 #### For gfx1151 (Strix Halo iGPU):
 
 ```cmd
-pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2/gfx1151/
+pip install --pre torch torchaudio torchvision rocm[devel] --index-url https://rocm.nightlies.amd.com/v2/gfx1151/
 ```
 
 #### For gfx1150 (Radeon 890M - Strix Point):
 
 ```cmd
-pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2-staging/gfx1150/
+pip install --pre torch torchaudio torchvision rocm[devel] --index-url https://rocm.nightlies.amd.com/v2-staging/gfx1150/
 ```
 
 #### For gfx103X-dgpu (RDNA 2):
 
 ```cmd
-pip install --pre torch torchaudio torchvision --index-url https://rocm.nightlies.amd.com/v2-staging/gfx103X-dgpu/
+pip install --pre torch torchaudio torchvision rocm[devel] --index-url https://rocm.nightlies.amd.com/v2-staging/gfx103X-dgpu/
 ```
 
 This will automatically install the latest PyTorch, torchaudio, and torchvision wheels with ROCm support.
@@ -152,12 +152,16 @@ Device: AMD Radeon RX 9070 XT
 
 WanGP supports multiple attention implementations via [triton-windows](https://github.com/woct0rdho/triton-windows/).
 
-First, install `triton-windows` in your virtual environment.  
-If you have an older version of Triton installed, uninstall it first:
+First, install `triton-windows` in your virtual environment.
+If you have an older version of Triton installed, uninstall it first.
+ROCm SDK needs to be initialized.
+Visual Studio environment should also be activated.
 
 ```cmd
 pip uninstall triton
 pip install triton-windows
+rocm-sdk init
+"C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvars64.bat" >nul 2>&1
 ```
 
 ### Supported attention implementations

From b356855f7d68481d2558379069a4d841ef9e509b Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 17:27:59 +0200
Subject: [PATCH 20/28] Add `packaging` module installation to
 `FlashAttention-2`

---
 docs/AMD-INSTALLATION.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 47dbd6a80..5d21b58d5 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -177,6 +177,7 @@ pip install "sageattention <2"
 git clone https://github.com/Dao-AILab/flash-attention.git
 cd flash-attention
 pip install ninja
+pip install packaging
 set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE && python setup.py install
 ```
 

From 9641ade88de1b64e17ef029d65366d77c249b706 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 17:36:54 +0200
Subject: [PATCH 21/28] Revise MIOpen stability notes and instructions

---
 docs/AMD-INSTALLATION.md | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 5d21b58d5..acfd6a98c 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -206,7 +206,13 @@ set FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE
 set TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
 ```
 
-MIOpen (AMD's cuDNN equivalent) is not yet stable; it frequently causes OOMs, crashes the display driver, and significantly increases generation times. Currently, it is recommended to use fast mode by setting `set MIOPEN_FIND_MODE=FAST`, or to disable it entirely by editing `wgp.py` and adding the following line below `import torch` (line 51):
+MIOpen (AMD’s equivalent of NVIDIA’s cuDNN) is not yet fully stable on several architectures; it can cause out-of-memory errors (OOMs), crash the display driver, or significantly increase generation times. Currently, it is recommended to either use fast mode by setting:
+
+```cmd
+set MIOPEN_FIND_MODE=FAST
+```
+
+or to disable MIOpen entirely by editing `wgp.py` and adding the following line below `import torch` (around line 51):
 
 ```cmd
 torch.backends.cudnn.enabled = False

From b7981b17dbbd43e49395b12f32d7e393d0696c0a Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 18:51:18 +0200
Subject: [PATCH 22/28] Fix formatting

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index acfd6a98c..6b39346d4 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -22,7 +22,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 ### **gfx1151** (RDNA 3.5 APU):
 * AMD Strix Halo APUs
 
-### **gfx1150** (RDNA 3.5 APU) 
+### **gfx1150** (RDNA 3.5 APU): 
 * AMD Radeon 890M (Ryzen AI 9 HX 370 - Strix Point)
 
 ### Also supported:

From 43332efd04282c51c3e974f89b85b619a9f32e29 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 18:52:15 +0200
Subject: [PATCH 23/28] Update AMD GPU support details in README

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index d3854f79c..0e8145fd2 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
 WanGP supports the Wan (and derived models) but also Hunyuan Video, Flux, Qwen, Z-Image, LongCat, Kandinsky, LTXV, LTX-2, Qwen3 TTS, Chatterbox, HearMula, ... with:
 - Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models)
 - Support for old Nvidia GPUs (RTX 10XX, 20xx, ...)
-- Support for AMD GPUs Radeon RX 76XX, 77XX, 78XX & 79XX, instructions in the Installation Section Below.
+- Support for AMD GPUs (RDNA 4, 3, 3.5, and 2) instructions in the Installation Section Below.
 - Very Fast on the latest GPUs
 - Easy to use Full Web based interface
 - Support for many checkpoint Quantized formats: int8, fp8, gguf, NV FP4, Nunchaku
@@ -303,7 +303,7 @@ For detailed installation instructions for different GPU generations:
 
 ### AMD
 For detailed installation instructions for different GPU generations:
-- **[Installation Guide](docs/AMD-INSTALLATION.md)** - Complete setup instructions for Radeon RX 76XX, 77XX, 78XX & 79XX
+- **[Installation Guide](docs/AMD-INSTALLATION.md)** - Complete setup instructions for RDNA 4, 3, 3.5, and 2
 
 ## 🎯 Usage
 

From 9bf280dc5f3c7dc59dcbb4104ec53f286f5730a9 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 18:54:40 +0200
Subject: [PATCH 24/28] Fix formatting

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b55a45915..886441787 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
 WanGP supports the Wan (and derived models) but also Hunyuan Video, Flux, Qwen, Z-Image, LongCat, Kandinsky, LTXV, LTX-2, Qwen3 TTS, Chatterbox, HearMula, ... with:
 - Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models)
 - Support for old Nvidia GPUs (RTX 10XX, 20xx, ...)
-- Support for AMD GPUs (RDNA 4, 3, 3.5, and 2) instructions in the Installation Section Below.
+- Support for AMD GPUs (RDNA 4, 3, 3.5, and 2), instructions in the Installation Section Below.
 - Very Fast on the latest GPUs
 - Easy to use Full Web based interface
 - Support for many checkpoint Quantized formats: int8, fp8, gguf, NV FP4, Nunchaku

From 9534c0999d6d07337eeab724938ef2f4c71a0604 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Wed, 4 Feb 2026 19:03:15 +0200
Subject: [PATCH 25/28] Add troubleshooting link for Wan2GP

---
 docs/AMD-INSTALLATION.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 6b39346d4..5114026c3 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -265,3 +265,5 @@ Known issues are tracked at: https://github.com/ROCm/TheRock/issues/808
 - [Supported GPU Architectures](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md)
 - [Roadmap](https://github.com/ROCm/TheRock/blob/main/ROADMAP.md)
 - [ROCm Documentation](https://rocm.docs.amd.com/)
+
+For additional troubleshooting guidance for Wan2GP, see [TROUBLESHOOTING.md](https://github.com/deepbeepmeep/Wan2GP/blob/main/docs/TROUBLESHOOTING.md).

From ae4a335543c4de715f9d6ea6d0d8251dfc395843 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Mon, 9 Feb 2026 13:28:22 +0200
Subject: [PATCH 26/28] Update

---
 docs/AMD-INSTALLATION.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 5114026c3..a1f7f3af6 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -30,7 +30,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 
 <br>
 
-> **Note:** If your GPU is not listed above, it is not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
+> **Note:** If your GPU is not listed above, it may not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 
 ## Requirements
 
@@ -166,7 +166,7 @@ rocm-sdk init
 
 ### Supported attention implementations
 
-- **SageAttention V1** (Requires the `.post26` wheel or newer):
+- **SageAttention V1** (Requires the `.post26` wheel or newer to fix Triton compilation issues without needing unofficial patches. Download it from [this](https://github.com/Comfy-Org/wheels/actions/runs/21343435018) URL)
 
 ```cmd
 pip install "sageattention <2"

From 7b955884f260b87e314122d6c651de3322d5e618 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Mon, 9 Feb 2026 13:30:49 +0200
Subject: [PATCH 27/28] Update

---
 docs/AMD-INSTALLATION.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index a1f7f3af6..9fc5802d2 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -30,7 +30,7 @@ Based on [TheRock's official support matrix](https://github.com/ROCm/TheRock/blo
 
 <br>
 
-> **Note:** If your GPU is not listed above, it may not supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
+> **Note:** If your GPU is not listed above, it may not be supported by TheRock on Windows. Support status and future updates can be found in the [official documentation](https://github.com/ROCm/TheRock/blob/main/SUPPORTED_GPUS.md).
 
 ## Requirements
 

From 86aec40832c99db1ebd3dc9017d22c8740c245c7 Mon Sep 17 00:00:00 2001
From: DELUXA <djernovevo@gmail.com>
Date: Mon, 9 Feb 2026 13:35:57 +0200
Subject: [PATCH 28/28] Update

---
 docs/AMD-INSTALLATION.md | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/docs/AMD-INSTALLATION.md b/docs/AMD-INSTALLATION.md
index 9fc5802d2..8663cb0db 100644
--- a/docs/AMD-INSTALLATION.md
+++ b/docs/AMD-INSTALLATION.md
@@ -212,10 +212,15 @@ MIOpen (AMD’s equivalent of NVIDIA’s cuDNN) is not yet fully stable on sever
 set MIOPEN_FIND_MODE=FAST
 ```
 
-or to disable MIOpen entirely by editing `wgp.py` and adding the following line below `import torch` (around line 51):
+Alternatively, you can disable MIOpen entirely by editing `wgp.py` and adding the following line below `import torch` (around line 51):
 
 ```cmd
-torch.backends.cudnn.enabled = False
+...
+:: /Lines already in the file/
+:: import torch
+torch.backends.cudnn.enabled = False # <-- Add this here
+:: import gc
+...
 ```
 
 To verify that it is disabled, or to enable verbose logging, you can set: