Update docs

Author: github-actions[bot]

_sources/autoapi/tilelang/carver/arch/cdna/index.rst.txt

@@ -30,9 +30,6 @@ Module Contents
    Bases: :py:obj:`tilelang.carver.arch.arch_base.TileDevice`
 
 
-   Represents the architecture of a computing device, capturing various hardware specifications.
-
-
    .. py:attribute:: target
 
 

_sources/autoapi/tilelang/carver/arch/cpu/index.rst.txt

@@ -30,9 +30,6 @@ Module Contents
    Bases: :py:obj:`tilelang.carver.arch.arch_base.TileDevice`
 
 
-   Represents the architecture of a computing device, capturing various hardware specifications.
-
-
    .. py:attribute:: target
 
 

_sources/autoapi/tilelang/carver/arch/cuda/index.rst.txt

@@ -92,9 +92,6 @@ Module Contents
    Bases: :py:obj:`tilelang.carver.arch.arch_base.TileDevice`
 
 
-   Represents the architecture of a computing device, capturing various hardware specifications.
-
-
    .. py:attribute:: target
 
 

_sources/autoapi/tilelang/carver/roller/hint/index.rst.txt

@@ -307,12 +307,12 @@ Module Contents
 
 
    .. py:property:: raxis_order
-      :type: tilelang.carver.roller.rasterization.List[int]
+      :type: List[int]
 
 
 
    .. py:property:: step
-      :type: tilelang.carver.roller.rasterization.List[int]
+      :type: List[int]
 
 
 

_sources/autoapi/tilelang/carver/roller/policy/tensorcore/index.rst.txt

@@ -30,15 +30,11 @@ Module Contents
 
 .. py:data:: logger
 
-.. py:class:: TensorCorePolicy(arch, tags = None)
+.. py:class:: TensorCorePolicy
 
    Bases: :py:obj:`tilelang.carver.roller.policy.default.DefaultPolicy`
 
 
-   Default Policy for fastdlight, a heuristic plan that tries to
-   minimize memory traffic and maximize parallelism.for BitBLAS Schedule.
-
-
    .. py:attribute:: wmma_k
       :type:  int
       :value: 16
@@ -65,67 +61,16 @@ Module Contents
 
    .. py:method:: infer_node_smem_usage(td, node)
 
-      Infers the shared memory usage of a node given a TileDict configuration.
-
-      :param td: The TileDict object containing the tile configuration.
-      :type td: TileDict
-      :param node: The node for which to infer the shared memory usage.
-      :type node: PrimFuncNode
-
-      :returns: The estimated amount of shared memory used by the node.
-      :rtype: int
-
-
 
    .. py:method:: get_node_reduce_step_candidates(node)
 
-      Calculates reduction step candidates for each reduction axis in a PrimFuncNode. General idea : use factor first, since it does not require extra boundary check. for large prime number, which is rare case, use power of 2.
-
-      :param node: The node for which to calculate reduction step candidates. It contains reduction axes (raxis)
-                   with their domains (dom.extent).
-      :type node: PrimFuncNode
-
-      :returns: A dictionary mapping axis variable names to lists of step candidates. For each axis in the node,
-                this function calculates possible step sizes. For axes with a large prime domain, it uses powers of 2
-                as step candidates; for others, it uses all factors of the domain.
-      :rtype: Dict[str, List[int]]
-
-
 
    .. py:method:: check_tile_shape_isvalid(td)
 
-      Checks if the tile shapes in the TileDict are valid for the nodes in this context.
-
-      Parameters:
-      - td (TileDict): The TileDict object containing tile shapes and other configurations.
-
-      Returns:
-      - bool: True if all tile shapes are valid, False otherwise.
-
-
 
    .. py:method:: compute_node_stride_map(node, td)
 
-      Computes the stride map for a given node based on the TileDict configuration.
-
-      :param node: The node for which to compute the stride map.
-      :type node: PrimFuncNode
-      :param td: The TileDict object containing the tile configuration.
-      :type td: TileDict
-
-      :returns: A tuple of dictionaries containing the output strides and tensor strides.
-      :rtype: Tuple[Dict, Dict]
-
-
 
    .. py:method:: plan_rasterization(td)
 
-      Plans the rasterization for the given TileDict. This function is not implemented yet.
-
-      :param td: The TileDict object to plan rasterization for.
-      :type td: TileDict
-
-      :raises RasterRationPlan: This function is not implemented yet.
-
-
 

_sources/autoapi/tilelang/jit/adapter/cython/adapter/index.rst.txt

@@ -134,6 +134,18 @@ Module Contents
 
 
 
+   .. py:attribute:: static_strides_map
+      :type:  Optional[Dict[tvm.tir.Var, Tuple[int, List[Tuple[int, int]]]]]
+      :value: None
+
+
+
+   .. py:attribute:: static_contiguous_list
+      :type:  Optional[List[tvm.tir.Var]]
+      :value: None
+
+
+
    .. py:attribute:: buffer_device_map
       :type:  Optional[Dict[tvm.tir.Var, Tuple[int, torch.device]]]
       :value: None

_sources/autoapi/tilelang/jit/adapter/dlpack/index.rst.txt

@@ -20,12 +20,8 @@ Classes
 Module Contents
 ---------------
 
-.. py:class:: TorchDLPackKernelAdapter(mod, params, result_idx)
+.. py:class:: TorchDLPackKernelAdapter
 
    Bases: :py:obj:`tilelang.jit.adapter.base.BaseKernelAdapter`
 
 
-   Helper class that provides a standard way to create an ABC using
-   inheritance.
-
-

_sources/autoapi/tilelang/jit/adapter/nvrtc/adapter/index.rst.txt

@@ -80,8 +80,6 @@ Module Contents
 
 
    .. py:attribute:: target
-      :value: None
-
 
 
    .. py:attribute:: verbose

_sources/autoapi/tilelang/jit/adapter/wrapper/index.rst.txt

@@ -493,6 +493,9 @@ Module Contents
    .. py:property:: prim_func
 
 
+   .. py:property:: device_func
+
+
 .. py:class:: TLNVRTCSourceWrapper(scheduled_ir_module, source, target, device_mod = None, host_mod = None, pass_configs = None)
 
    Bases: :py:obj:`TLCUDASourceWrapper`

_sources/autoapi/tilelang/language/proxy/index.rst.txt

@@ -25,6 +25,7 @@ Classes
    tilelang.language.proxy.BufferProxy
    tilelang.language.proxy.BaseTensorProxy
    tilelang.language.proxy.TensorProxy
+   tilelang.language.proxy.StridedTensorProxy
    tilelang.language.proxy.FragmentBufferProxy
    tilelang.language.proxy.SharedBufferProxy
    tilelang.language.proxy.LocalBufferProxy
@@ -54,7 +55,7 @@ Module Contents
    .. py:method:: __getitem__(keys)
 
 
-   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32')
+   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32', strides = None)
 
       Create a buffer from a pointer, shape, and data type.
 
@@ -96,7 +97,7 @@ Module Contents
    .. py:method:: __getitem__(keys)
 
 
-   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32')
+   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32', strides = None)
 
       Create a buffer from a pointer, shape, and data type.
 
@@ -116,7 +117,23 @@ Module Contents
    Main tensor proxy class for global scope buffers.
 
    This class implements the default tensor proxy with global memory scope,
-   inheriting all functionality from BaseTensorProxy without modifications.
+   the tensor should be by default contiguous.
+
+
+   .. py:method:: __call__(shape, dtype = 'float32', data=None)
+
+
+.. py:class:: StridedTensorProxy
+
+   Bases: :py:obj:`BaseTensorProxy`
+
+
+   Main tensor proxy class for global scope buffers, with strides supported.
+
+   This class implements the default tensor proxy with global memory scope, with the stride information required.
+
+
+   .. py:method:: __call__(shape, strides, dtype = 'float32')
 
 
 .. py:class:: FragmentBufferProxy
@@ -182,7 +199,7 @@ Module Contents
    .. py:method:: __setitem__(key, value)
 
 
-   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32')
+   .. py:method:: from_ptr(pointer_var, shape, dtype = 'float32', strides = None)
       :classmethod:
 
 
@@ -202,5 +219,5 @@ Module Contents
    :rtype: PrimExpr
 
 
-.. py:function:: make_tensor(ptr, shape, dtype = 'float32')
+.. py:function:: make_tensor(ptr, shape, dtype = 'float32', strides = None)