Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/tile-ai/tilelang
/ functions
Functions
7,254 in github.com/tile-ai/tilelang
⨍
Functions
7,254
◇
Types & classes
525
↳
Endpoints
224
↓ 1 callers
Method
update_lib_code
(self, code: str)
tilelang/jit/adapter/wrapper.py:572
↓ 1 callers
Method
update_lib_code
(self, code: str)
tilelang/jit/adapter/wrapper.py:874
↓ 1 callers
Method
update_lib_code
(self, code: str)
tilelang/jit/adapter/wrapper.py:927
↓ 1 callers
Method
update_lib_code
Update library code and generate host dispatch function. Entry point for code generation. Walks the host IR to extract kernel call si
tilelang/jit/adapter/nvrtc/wrapper.py:544
↓ 1 callers
Function
valid_loop_not_frag
(dtype: T.dtype = T.bfloat16, accum_dtype: T.dtype = T.float32, num_threads: int = 128)
testing/python/analysis/test_tilelang_fragment_loop_checker.py:94
↓ 1 callers
Function
valid_loop_not_use_loop_var
(dtype: T.dtype = T.bfloat16, accum_dtype: T.dtype = T.float32, num_threads: int = 128)
testing/python/analysis/test_tilelang_fragment_loop_checker.py:72
↓ 1 callers
Function
valid_loop_serial
(dtype: T.dtype = T.bfloat16, accum_dtype: T.dtype = T.float32, num_threads: int = 128)
testing/python/analysis/test_tilelang_fragment_loop_checker.py:115
↓ 1 callers
Method
validate
(self)
examples/autodd/tilelang_buggy.py:78
↓ 1 callers
Function
validate_gemm_ab_dtypes
Validate mixed A/B dtypes for GEMM tile ops. TS variants (A in TMEM) skip validation because A/B dtypes may legitimately differ. Only TCGEN05
tilelang/language/dtypes.py:313
↓ 1 callers
Function
validate_parameters
Validate parameters - redundant check
examples/autodd/tilelang_buggy.py:40
↓ 1 callers
Function
validate_tensor_match
(a, b, tolerance=1e-8, tensor_name="tensor", should_raise=True)
examples/deepseek_v32/fp8_lighting_indexer.py:23
↓ 1 callers
Function
var_init_kernel
(iv, tld)
testing/python/amd/test_tilelang_hip_codegen.py:406
↓ 1 callers
Function
vectorize_access_legalize
(M: int = 64, N: int = 64, M_offset: int = 2, N_offset: int = 2)
testing/python/transform/test_tilelang_transform_legalize_safe_memory_access.py:81
↓ 1 callers
Function
vectorize_access_legalize
(M: int = 64, N: int = 64)
testing/python/transform/test_tilelang_transform_legalize_vectorized_loop.py:7
↓ 1 callers
Function
vectorize_access_with_atmoic_add_legalize
(M: int = 64, N: int = 64, M_offset: int = 2, N_offset: int = 2)
testing/python/transform/test_tilelang_transform_legalize_safe_memory_access.py:121
↓ 1 callers
Function
vectorize_test
(N, M, stride_A, stride_B)
testing/python/language/test_tilelang_language_vectorize.py:10
↓ 1 callers
Function
vectorize_test_all_dtypes
(dtype, vec_num)
testing/python/language/test_tilelang_language_vectorize.py:117
↓ 1 callers
Function
vectorize_test_invariant_index
(N, M, K)
testing/python/language/test_tilelang_language_vectorize.py:63
↓ 1 callers
Function
vectorized
The vectorized For statement. Parameters ---------- start : PrimExpr The minimum value of iteration. stop : PrimExpr
tilelang/language/loop.py:329
↓ 1 callers
Function
vectorized_cast_kernel
(M: int, dtype_A: str, dtype_B: str)
testing/python/language/test_tilelang_language_vectorized_cast.py:8
↓ 1 callers
Function
verify_outputs
(outputs, refs, batch_sizes_list, atol=1e-2, rtol=1e-2)
examples/grouped_gemm/example_grouped_gemm_fwd_ptr.py:96
↓ 1 callers
Function
vertical_slash_sparse_attention
( query: torch.Tensor, # [BATCH, N_HEADS, N_CTX, D_HEAD] key: torch.Tensor, # [BATCH, N_HEADS, N_CTX
examples/minference/example_vertical_slash_sparse_attn.py:484
↓ 1 callers
Function
view_shape_mismatch_test
(N, M, dtype, new_dtype=None)
testing/python/language/test_tilelang_language_view.py:57
↓ 1 callers
Function
view_test
(N, M, dtype, new_dtype=None)
testing/python/language/test_tilelang_language_view.py:9
↓ 1 callers
Method
visit
(self, node: ast.AST, parent: "ast.AST | None", field: "str | None", inside_list: bool)
tilelang/autodd.py:433
↓ 1 callers
Method
visit
(self, node: ast.AST, parent: "ast.AST | None", field: "str | None", inside_list: bool)
tilelang/autodd.py:495
↓ 1 callers
Function
walk_indice
(expr)
tilelang/carver/roller/shape_inference/tir.py:311
↓ 1 callers
Function
weight_dequant
(weight, scale)
examples/deepseek_v32/inference/model.py:514
↓ 1 callers
Method
wgmma_rs_atom
Emit a single WGMMA RS instruction for atom ``(inst_m_idx, inst_n_idx, ki)``. Must be called between a ``wgmma_fence_a``/``wgmma_fence_c``/``
tilelang/cuda/intrinsics/macro/wgmma_macro_generator.py:510
↓ 1 callers
Function
while_loop
()
testing/python/language/test_tilelang_language_frontend_v2.py:325
↓ 1 callers
Method
with_default_adapter
(self, adapter: BaseKernelAdapter)
tilelang/profiler/__init__.py:58
↓ 1 callers
Method
worker
(self, wid: int)
tilelang/autodd.py:1198
↓ 1 callers
Function
wrap_label
(s: str, width: int = 42)
maint/scripts/test_perf_regression.py:111
Method
A
(self)
tilelang/tileop/gemm/gemm_base.py:112
Method
A
(self)
tilelang/tileop/gemm/__init__.py:42
Method
A
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:76
Method
APtr
(self)
tilelang/tileop/gemm/__init__.py:54
Method
ARegion
(self)
tilelang/tileop/gemm/gemm_base.py:124
Method
ARegion
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:92
Function
ASTPrinter
A visitor pass that renders the TileLang AST hierarchy in a visual tree format. Comparing with TL script, this printer is more suitable for
tilelang/analysis/ast_printer.py:109
Method
A_base_offsets
Get base offsets for each dimension of A region
tilelang/tileop/gemm/gemm_base.py:221
Function
AddWrapperForSingleBufStore
Creates a TVM pass that wraps single buffer stores with parallel loops. This transformation adds T.Parallel wrappers around buffer stores th
tilelang/transform/add_bufstore_wrapper.py:6
Function
AnnotateDeviceRegions
AnnotateDeviceRegions Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:217
Function
AnnotateReadOnlyParams
Annotate read-only handle parameters for PrimFuncs. Adds attribute `tl.readonly_param_indices` listing param indices that are never written,
tilelang/transform/__init__.py:239
Function
AnnotateWarpGroupRegAlloc
Inject set_max_nreg calls into warp-specialized functions. This pass analyzes the function to collect register hints from set_max_nreg and no
tilelang/cuda/transform/__init__.py:128
Function
Assert
Create an assertion statement. Parameters ---------- condition : PrimExpr The PrimExpr to test. message : str The ou
tilelang/language/ast/ir.py:852
Function
AtomicAddRet
Perform atomic addition and return the previous value. This is the same as AtomicAdd since nvvm.atomicrmw always returns old value.
tilelang/contrib/cutedsl/atomic.py:154
Function
AtomicAddx2
Vectorized atomic add for 2 consecutive elements. Uses PTX atom.add.v2.f32 for float32 or atom.add.noftz.v2.f16 for float16. Args: d
tilelang/contrib/cutedsl/atomic.py:176
Function
AtomicAddx4
Vectorized atomic add for 4 consecutive float32 elements. Uses PTX atom.global.add.v4.f32 for true vectorized atomic operation on SM90+. Arg
tilelang/contrib/cutedsl/atomic.py:241
Function
AtomicLoad
Perform atomic load with specified memory ordering. Args: ptr: Pointer to load from memory_order: TileLang memory order ID (0=rel
tilelang/contrib/cutedsl/atomic.py:463
Function
AtomicMaxRet
Perform atomic maximum and return the previous value.
tilelang/contrib/cutedsl/atomic.py:355
Function
AtomicMinRet
Perform atomic minimum and return the previous value.
tilelang/contrib/cutedsl/atomic.py:433
Function
AtomicStore
Perform atomic store with specified memory ordering. Args: ptr: Pointer to store to value: Value to store memory_order: T
tilelang/contrib/cutedsl/atomic.py:562
Method
B
(self)
tilelang/tileop/gemm/gemm_base.py:116
Method
B
(self)
tilelang/tileop/gemm/__init__.py:46
Method
B
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:84
Method
BPtr
(self)
tilelang/tileop/gemm/__init__.py:58
Method
BRegion
(self)
tilelang/tileop/gemm/gemm_base.py:128
Method
BRegion
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:100
Method
B_base_offsets
Get base offsets for each dimension of B region
tilelang/tileop/gemm/gemm_base.py:226
Method
C
(self)
tilelang/tileop/gemm/gemm_base.py:120
Method
C
(self)
tilelang/tileop/gemm/__init__.py:50
Method
C
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:88
Function
CPUPassPipelineBody
(mod: IRModule, target: Target)
tilelang/cpu/pipeline.py:18
Method
CPtr
(self)
tilelang/tileop/gemm/__init__.py:62
Method
CRegion
(self)
tilelang/tileop/gemm/gemm_base.py:132
Method
CRegion
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:104
Function
CUDAPassPipelineBody
(mod: IRModule, target: Target)
tilelang/cuda/pipeline.py:141
Function
CUDASourceCodeKernel
Launch a kernel from CUDA source code or a CUDA source file. The code must follows the following rules: 1. The kernel source must be a valid
tilelang/language/kernel.py:372
Method
C_base_offsets
Get base offsets for each dimension of C region
tilelang/tileop/gemm/gemm_base.py:231
Method
C_coords
(self)
tilelang/tileop/gemm/gemm_base.py:180
Function
ClusterPlanning
ClusterPlanning Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:19
Function
ColumnMajorInterleaved
(i: int, j: int)
tilelang/layout/gemm_sp.py:138
Function
ConfigIndexBitwidth
Config index bitwidth. Returns ------- fpass : tvm.transform.Pass The result pass ----
tilelang/transform/__init__.py:289
Method
E
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:80
Method
ERegion
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:96
Function
Else
Create an else. Returns ------- res : frame.ElseFrame The result ElseFrame.
tilelang/language/ast/ir.py:1122
Function
FlattenBuffer
FlattenBuffer Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:301
Function
FragmentLoopChecker
When using T.Parallel over a local/fragment buffer, there are several restrictions: to ensure that the parallelization is valid. 1. The
tilelang/analysis/fragment_loop_checker.py:100
Function
FuseMBarrierArriveExpectTx
Fuse simple expect_tx -> TMA issue -> arrive back into arrive_and_expect_tx.
tilelang/cuda/transform/__init__.py:67
Function
HoistBroadcastValues
TVM Pass: HoistBroadcastValues. This pass scans the TIR for Broadcast operations involving immediate constants (IntImm, FloatImm). It ex
tilelang/transform/hoist_broadcast_values.py:71
Function
HoistGlobalBufferAllocations
Hoist global buffer allocations to the top of the block (host side). Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:334
Function
HoistNonRestrictParams
()
tilelang/transform/__init__.py:345
Function
If
Create an if node. Parameters ---------- condition : PrimExpr The condition of if statement, executes the true branch if the cond
tilelang/language/ast/ir.py:1092
Function
IfStmtBinding
IfStmtBinding Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:140
Function
InjectAssumes
Inject Assumes for natural shape boundary conditions. And convert Assumes in Evaluate(Call(...)) form (tvm builtin assume call) to AttrNode form.
tilelang/transform/__init__.py:101
Function
InjectFenceProxy
InjectFenceProxy Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/cuda/transform/__init__.py:99
Function
InjectPTXAsyncCopy
Deprecated alias of `LowerPTXAsyncCopy`.
tilelang/transform/__init__.py:284
Function
InjectSoftwarePipeline
InjectSoftwarePipeline Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:79
Function
InjectTcgen05Fence
Inject tcgen05.fence::before_thread_sync / after_thread_sync at conservative TCGEN05/TMEM synchronization boundaries on Blackwell (SM100+) tar
tilelang/cuda/transform/__init__.py:110
Function
InstructionAnnotation
Annotate tile operations with coarse-grained instruction kind. This pass runs before LayoutInference and LowerTileOp. It adds a ``tl_instruc
tilelang/transform/__init__.py:41
Method
K
(self)
tilelang/tileop/gemm/gemm_base.py:82
Method
K
(self)
tilelang/tileop/gemm/__init__.py:74
Method
K
(self)
tilelang/tileop/gemm_sp/gemm_sp_base.py:42
Function
Kernel
Tools to quickly construct a GPU kernel launch frame. Parameters ---------- blocks : int A list of extent, can be 1-3 dimension,
tilelang/language/kernel.py:267
Function
LayoutInference
LayoutInference Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:57
Function
LayoutReducer
Return a TVM transform pass that performs layout reduction/normalization. This wrapper delegates to the underlying FFI implementation and re
tilelang/transform/__init__.py:388
Function
LayoutVisual
(formats: str | Sequence[str] = "")
tilelang/analysis/layout_visual.py:103
Function
LegalizeNegativeIndex
Legalize negative indices in buffer loads. Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:90
Function
LegalizeSafeMemoryAccess
LegalizeLoopVectorize Returns ------- fpass : tvm.transform.Pass The result pass
tilelang/transform/__init__.py:184
← previous
next →
3,301–3,400 of 7,254, ranked by callers