[Doc] Clean content relate to removed/deprecated feature (#5415)

Clean content relate to removed/deprecated feature

Update known issue with dependencies problem which causes the issue that we can not install using one command

---------

Co-authored-by: ZhaoqiongZ <[email protected]>

Author: tye1

docs/tutorials/features/nhwc.md

@@ -195,7 +195,9 @@ auto src_mem = memory(src_md, src_data_ptr, engine);
 * **NCHW** - create `memory::desc` with *any* card for 'input', 'output' and 'weight'; query proposed `memory::desc` from convolution primitive;
 * **NHWC** - create `memory::desc` with `format_tag::nhwc` for 'input' and 'output', use *any* for 'weight'; if we use `hwio` for 'weight' convolution primitive will be created with gemm rather jit avx512.
 
-## Channels Last 1D support on XPU
+## Channels Last 1D support on XPU (Deprecated)
+
+**Note:** Channels Last 1D support on XPU APIs `torch.xpu.to_channels_last_1d()` and `torch.xpu.is_contiguous_channels_last_1d()` will be deprecated in future releases.
 
 Both stock PyTorch and Intel® Extension for PyTorch\* support Channels Last(2D) and Channels Last 3D, however, regarding Channels Last 1D, they are different. Stock PyTorch doesn't support Channels Last 1D, while XPU could supply limited support for Channels Last 1D.
 We only support Channels Last 1D memory format in these operators: Conv1D, BatchNorm1D, MaxPool1D, Concat, binary add, binary div, upsample linear and upsample nearest.

docs/tutorials/features/profiler_legacy.md

@@ -1,6 +1,6 @@
-Legacy Profiler Tool (Deprecated)
+Legacy Profiler Tool (Removed)
 ================================
 
 ## Introduction
 
-The legacy profiler tool will be deprecated from Intel® Extension for PyTorch* very soon. Please use [Kineto Supported Profiler Tool](./profiler_kineto.md) instead for profiling operators' executing time cost on Intel® GPU devices.
+The legacy profiler tool has been removed from Intel® Extension for PyTorch\*. Please use [Kineto Supported Profiler Tool](./profiler_kineto.md) instead for profiling operators' executing time cost on Intel® GPU devices.

docs/tutorials/known_issues.md

@@ -26,6 +26,9 @@ Troubleshooting
 - **Problem**: RuntimeError: Can't add devices across platforms to a single context. -33 (PI_ERROR_INVALID_DEVICE).
   - **Cause**: If you run Intel® Extension for PyTorch\* in a Windows environment where Intel® discrete GPU and integrated GPU co-exist, and the integrated GPU is not supported by Intel® Extension for PyTorch\* but is wrongly identified as the first GPU platform.
   - **Solution**: Disable the integrated GPU in your environment to work around. For long term, Intel® Graphics Driver will always enumerate the discrete GPU as the first device so that Intel® Extension for PyTorch\* could provide the fastest device to end framework users in such co-exist scenario based on that.
+- **Problem**: RuntimeError: Failed to load the backend extension: intel_extension_for_pytorch. You can disable extension auto-loading with TORCH_DEVICE_BACKEND_AUTOLOAD=0.
+  - **Cause**: If you import any third party library such as Transformers before `import torch`, and the third party library has dependency to torch and then implicitly autoloads intel_extension_for_pytorch, which introduces circle import.
+  - **Solution**: Disable extension auto-loading with TORCH_DEVICE_BACKEND_AUTOLOAD=0.
 
 ## Library Dependencies
 
@@ -89,15 +92,6 @@ Troubleshooting
     source {dpcpproot}/env/vars.sh
     ```
 
-- **Problem**: RuntimeError: Cannot find a working triton installation. Either the package is not installed or it is too old. More information on installing Triton can be found at https://github.com/openai/triton
-  - **Cause**: No pytorch-triton-xpu installed
-  - **Solution**: Resolve the issue with following command:
-
-    ```bash
-    # Install correct version of pytorch-triton-xpu
-    pip install --pre pytorch-triton-xpu==3.1.0+91b14bf559  --index-url https://download.pytorch.org/whl/nightly/xpu
-    ```
-
 - **Problem**: LoweringException: ImportError: cannot import name 'intel' from 'triton._C.libtriton'
   - **Cause**: Installing Triton causes pytorch-triton-xpu to stop working.
   - **Solution**: Resolve the issue with following command:
@@ -111,6 +105,14 @@ Troubleshooting
     pip install --pre pytorch-triton-xpu==3.1.0+91b14bf559  --index-url https://download.pytorch.org/whl/nightly/xpu
     ```
 
+- **Problem**: ERROR: can not install dpcpp-cpp-rt and torch==2.6.0 because these packages version has conflicting dependencies.
+  - **Cause**: The intel-extension-for-pytorch v2.6.10+xpu uses Intel DPC++ Compiler 2025.0.4 to get a crucial bug fix in unified runtime, while torch v2.6.0+xpu is pinned with 2025.0.2, so we can not install PyTorch and intel-extension-for-pytorch in one pip installation command.
+  - **Solution**: Install PyTorch and intel-extension-for-pytorch with seperate commands.
+    ```
+    python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu
+    python -m pip install intel-extension-for-pytorch==2.6.10+xpu oneccl_bind_pt==2.6.0+xpu --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
+    ```
+    
 - **Problem**: ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
 
   ```
@@ -123,6 +125,10 @@ Troubleshooting
   - **Cause**: The intel-extension-for-pytorch v2.6.10+xpu uses Intel DPC++ Compiler 2025.0.4 to get a crucial bug fix in unified runtime, while torch v2.6.0+xpu is pinned with 2025.0.2.
   - **Solution**: Ignore the Error since actually torch v2.6.0+xpu is compatible with Intel Compiler 2025.0.4.
 
+- **Problem**: RuntimeError: oneCCL: ze_handle_manager.cpp:226 get_ptr: EXCEPTION: unknown memory type, when executing DLRMv2 BF16 training on 4 cards Intel® Data Center GPU Max platform. 
+  - **Cause**: Issue exists in the default sycl path of oneCCL 2021.14 which uses two IPC exchanges. 
+  - **Solution**: Use `export CCL_ATL_TRANSPORT=ofi` to work around. 
+
 ## Performance Issue
 
 - **Problem**: Extended durations for data transfers from the host system to the device (H2D) and from the device back to the host system (D2H).

docs/tutorials/releases.md

@@ -39,6 +39,7 @@ Intel® Extension for PyTorch\* v2.6.10+xpu is the new release which supports In
 ### Breaking Changes
 
 - Intel® Data Center GPU Flex Series support is being deprecated and will no longer be available starting from the release after v2.6.10+xpu.
+- Channels Last 1D support on XPU is being deprecated and will no longer be available starting from the release after v2.6.10+xpu.
 
 ### Known Issues