↓ 2 callersFunctionkernel(M, N, dtype, op, src_scope, dst_scope, threads, batch)
testing/python/language/test_tilelang_language_reduce.py:101
↓ 2 callersFunctionkernel(
A: T.Tensor((M, N), dtype),
B: T.Tensor((M, N), dtype),
C: T.Tensor((M,
testing/python/jit/test_tilelang_jit_tvm_ffi.py:403
↓ 2 callersMethodldmatrix_e(self, E_local_buf: Buffer, E_shared_buf: Buffer, inst_i: PrimExpr, warp_m: PrimExpr, ki: PrimExpr, ki_slot: P
tilelang/cuda/intrinsics/macro/wgmma_sp_macro_generator.py:431
↓ 2 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, num_stages, thread_num, enable_rasteration, dtype=T.float16, accum_dtype=
examples/gemm/example_gemm_autotune.py:188
↓ 2 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, num_stages, thread_num, enable_rasteration, dtype=T.float16, accum_dtype=
examples/gemm/example_gemm_advanced_autotune.py:246
↓ 2 callersFunctionmatmul(A, B, C, block_M, block_N, block_K, split_k, dtype=T.float16, accum_dtype=T.float32, out_dtype=T.float32)
examples/gemm_splitk/example_tilelang_gemm_splitk.py:6
↓ 2 callersFunctionmatmul(A, B, C, block_M, block_N, block_K, split_k, dtype=T.float16, accum_dtype=T.float32, out_dtype=T.float32)
examples/gemm_splitk/example_tilelang_gemm_splitk_vectorize_atomicadd.py:6
↓ 2 callersFunctionmatmul(
A,
B,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_dtype,
examples/gemm_sm100/gemm_tcgen5mma.py:13
↓ 2 callersFunctionmatmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/gemm_sm100/gemm_mma.py:13
↓ 2 callersFunctionmatmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/warp_specialize/example_warp_specialize_gemm_barrierpipe_stage2.py:6
↓ 2 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_cluster.py:7
↓ 2 callersFunctionmatmul(M, N, K, block_M, block_N, block_K, trans_A=False, trans_B=False, dtype=T.float32, accum_dtype=T.float32)
testing/python/cpu/test_tilelang_cpu_tgemm.py:15
↓ 2 callersFunctionmatmul_nested_pipa(
M,
N,
K,
block_M,
block_N,
block_K,
in_dtype,
out_dtype,
accum_dtype,
testing/python/analysis/test_tilelang_nested_loop_checker.py:364
↓ 2 callersFunctionmatmul_simdgroup(M, N, K, block_M=64, block_N=64, block_K=32, dtype=T.float16, accum_dtype=T.float32)
benchmark/matmul_metal/benchmark_matmul_metal.py:21
↓ 2 callersFunctionmatmul_warp_specialize_copy_gemm_0_1(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/warp_specialize/example_warp_specialize_gemm_copy_gemm_0_1.py:6
↓ 2 callersFunctionmatvec_A(R, x1, x2, buf, y1, y2, tilesize, n_stream)
examples/deepseek_mhc/example_mhc_bwd.py:52
↓ 2 callersFunctionmhc_post_tilelang(a, b, c, d, x, hc: int, hidden: int, n_thr: int = 128, h_blk: int = 1024)
examples/deepseek_mhc/example_mhc_post.py:12
↓ 2 callersFunctionmla_decode_tilelang(batch, h_q, h_kv, max_seqlen_pad, dv, dpe, block_N, block_H, num_split, block_size, softmax_scale=None)
examples/deepseek_mla/example_mla_decode_paged.py:16
↓ 2 callersFunctionnaive_nsar""" Args: q (torch.Tensor): Queries of shape `[B, T, HQ, K]` if `head_first=False` else `[B, HQ, T, K]`. k (torch.Ten
examples/deepseek_nsa/benchmark/benchmark_nsa_fwd.py:306
↓ 2 callersFunctionnative_sparse_attention(Q, K, V, BlockIndices, dim, is_causal, scale=None, block_size=64, groups=1, selected_blocks=16)
examples/deepseek_nsa/example_tilelang_nsa_fwd.py:18
↓ 2 callersFunctionnative_sparse_attention(
Q,
K,
V,
BlockIndices,
dim, # Embedding dimension per head
scale=None,
block_si
examples/deepseek_nsa/example_tilelang_nsa_decode.py:20
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
output_dtype,
)
examples/gdn/example_wy_fast.py:34
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
state_dtype,
)
examples/gdn/example_chunk_delta_h.py:70
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
gate_dtype,
state_dtype,
)
examples/gdn/example_chunk_delta_bwd.py:90
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
)
examples/gdn/example_chunk_o.py:45
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
gate_dtype,
state_dtype,
examples/gdn/example_chunk_o_bwd.py:82
↓ 2 callersFunctionprepare_output(
B,
S,
H,
chunk_size,
sub_chunk_size,
output_dtype,
)
examples/kda/chunk_inter_solve_fused.py:40
↓ 2 callersFunctionprepare_output(
B,
S,
H,
chunk_size,
sub_chunk_size,
output_dtype,
)
examples/kda/chunk_intra_token_parallel.py:33
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
state_dtype,
)
examples/kda/chunk_delta_h_fwd.py:48
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
use_qg,
use_kg,
output_dtype,
)
examples/kda/wy_fast.py:24
↓ 2 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
)
examples/kda/chunk_o.py:34