Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_parcompile.py:34
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_tvm_ffi.py:30
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), accum_dt
testing/python/jit/test_tilelang_jit_nullptr.py:11
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_gemm_cython.py:30
Functionmain(
A: T.Tensor((N,), dtype),
B: T.Tensor((N,), dtype),
C: T.Tensor((N,), dt
testing/python/jit/test_tilelang_jit_cython.py:18
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_gemm.py:31
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_callback.py:30
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/jit/test_tilelang_jit_nvrtc.py:30
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/metal/test_metal_codegen_linux.py:15
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), accum_dt
testing/python/metal/test_metal_gemm_v2_linux.py:16
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/webgpu/test_webgpu_codegen.py:9
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M, N), dtype),
testing/python/autotune/test_tilelang_autotune_do_not_specialize.py:41
Functionmain(
A: T.Buffer((M, K), dtype),
B: T.Buffer((K, N), dtype),
C: T.Buffer((M, N), dtype),
testing/python/transform/test_tilelang_transform_producer_consumer_ws.py:15
Functionmain(
x: T.Tensor((128,), T.float32),
y: T.Tensor((128,), T.float32),
)
testing/python/transform/test_readonly_param_const_codegen.py:8
Functionmain(
A: T.Tensor((32,), dtype),
B: T.Tensor((16,), dtype),
C: T.Tensor((8,), dtype),
testing/python/transform/test_tilelang_transform_hoist_broadcast_values.py:15
Functionmain(
A: T.Tensor((1024,), dtype=T.bfloat16),
B: T.Tensor((1024,), dtype=T.bfloat16),
testing/python/transform/test_tilelang_transform_decouple_type_cast.py:336
Functionmain(
Q: T.Tensor(shape, dtype),
K: T.Tensor(shape, dtype),
V: T.Tensor(shape,
testing/python/transform/test_tilelang_transform_config_index_bitwidth.py:100
Functionmain(
A: T.Tensor((M, N), dtype),
B: T.Tensor((M, N), dtype),
)
testing/python/math/test_math_fast_math.py:69
Functionmain(
A: T.Tensor((32, 32), T.float32),
B: T.Tensor((32, 32), T.float32),
)
testing/python/math/test_math_ieee_math.py:191
Functionmain(
A: T.Tensor((M * 2,), dtype=dtype_tl),
B: T.Tensor((M * 2,), dtype=dtype_tl),
C: T.T
testing/python/cuda/test_cuda_f32x2_intrinsics.py:43
Functionmain(
A: T.Tensor((M, K), in_dtype),
B: T.Tensor((N, K), in_dtype),
C: T.Tensor((M, N), ou
testing/python/kernel/test_tilelang_kernel_bf16_gemm_tcgen5_ts.py:21
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((M, N),
testing/python/kernel/test_tilelang_kernel_gemm.py:27
Functionmain(
A: T.Tensor((M, K), in_dtype),
B: T.Tensor((N, K), in_dtype),
C: T.Tensor((M, N), ou
testing/python/kernel/test_tilelang_kernel_gemm_sm75.py:10
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor((batch,
testing/python/kernel/test_tilelang_kernel_gemm_batched.py:28
Functionmain(
A: T.Tensor((M, K), in_dtype),
B: T.Tensor((N, K), in_dtype),
C: T.Tensor((M, N), ou
testing/python/kernel/test_tilelang_kernel_int8_gemm_tcgen5.py:15
Functionmain(
A: T.Tensor(A_shape, in_dtype),
B: T.Tensor(B_shape, in_dtype),
C: T.Tensor(C_shape,
testing/python/kernel/test_tilelang_kernel_gemm_simt.py:78
Functionmain(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/kernel/test_tilelang_kernel_gemm_with_stride.py:9
Functionmain_func(
A: T.Tensor((M, N), dtype),
B: T.Tensor((M, N), dtype),
C: T.Tensor((M,
testing/python/math/test_math_ieee_math.py:29
Functionmain_no_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/warp_specialize/example_warp_specialize_flashmla.py:21
Functionmain_no_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/example_mla_decode.py:121
Functionmain_no_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/example_mla_decode_ws.py:287
Functionmain_no_split(
Q: T.Tensor([batch, h_q, dv], dtype),
Q_pe: T.Tensor([batch, h_q, dpe], dtype),
KV:
examples/deepseek_mla/example_mla_decode_paged.py:134
Functionmain_no_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/amd/benchmark_mla_decode_amd_tilelang.py:139
Functionmain_no_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/experimental/example_mla_decode_kv_fp8.py:26
Functionmain_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/example_mla_decode.py:23
Functionmain_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/example_mla_decode_ws.py:37
Functionmain_split(
Q: T.Tensor([batch, h_q, dv], dtype),
Q_pe: T.Tensor([batch, h_q, dpe], dtype),
KV:
examples/deepseek_mla/example_mla_decode_paged.py:28
Functionmain_split(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/amd/benchmark_mla_decode_amd_tilelang.py:46
Functionmain_split_persistent(
Q: T.Tensor([batch, heads, dim], dtype),
Q_pe: T.Tensor([batch, heads, pe_dim], dtype),
examples/deepseek_mla/example_mla_decode_persistent.py:27
Functionmatmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/gemm/example_gemm.py:6
Functionmatmul(
A,
B,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_dtype,
examples/gemm_fp8/example_tilelang_gemm_fp8_sm100.py:14
Functionmatmul_kernel_jit(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A=False,
trans_B=True,
in_dtyp
testing/python/jit/test_tilelang_jit_parcompile.py:11
Functionmatmul_kernel_with_barrier(
M,
N,
K,
block_M,
block_N,
block_K,
mbars,
trans_A,
trans_B,
in_dtyp
testing/python/jit/test_tilelang_jit_cutedsl.py:114
Functionmatmul_non_persistent(A, B, block_M, block_N, block_K, threads, num_stages, dtype=T.float16, accum_dtype=T.float32)
examples/gemm/example_gemm_persistent.py:8
Functionmatmul_persistent(
A, B, block_M, block_N, block_K, threads, num_stages, dtype=T.float16, accum_dtype=T.float32, use_persis
examples/gemm/example_gemm_persistent.py:36