↓ 2 callersFunctiontilelang_chunk_fwd_o(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_o.py:59
↓ 2 callersFunctiontilelang_chunk_gated_delta_rule_bwd_dhu(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_delta_bwd.py:187
↓ 2 callersFunctiontilelang_chunk_gated_delta_rule_fwd_h(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_delta_h.py:102
↓ 2 callersFunctiontilelang_chunk_local_cumsum_scalar(
# task config
B,
S,
H,
chunk_size=64,
is_varlen=False,
head_first=False,
rev
examples/gdn/example_cumsum.py:24
↓ 2 callersFunctiontilelang_chunk_o_bwd_dqkwg(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_o_bwd.py:114
↓ 2 callersFunctiontilelang_chunk_scaled_dot_kkt_fwd(
# task config
B,
S,
H,
DK,
chunk_size=64,
input_dtype=T.bfloat16,
output_dty
examples/gdn/example_chunk_scaled_dot_kkt.py:53
↓ 2 callersFunctiontilelang_recompute_w_u_fwd(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
gate_dtype,
examples/gdn/example_wy_fast.py:48
↓ 2 callersFunctiontilelang_wy_fast_bwd(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_wy_fast_bwd_split.py:99
↓ 2 callersFunctiontilelang_wy_fast_bwd_split(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_wy_fast_bwd_split.py:251
↓ 2 callersFunctiontl_fused_chunk_bwd_kernel(
B,
S,
H,
DK,
DV,
dtype: T.dtype = T.float16,
scale: float = None,
)
examples/linear_attention/example_linear_attn_bwd.py:13
↓ 2 callersFunctiontl_fused_chunk_fwd_kernel(
B,
S,
H,
DK,
DV,
dtype: T.dtype = T.float16,
scale: float = None,
)
examples/linear_attention/example_linear_attn_fwd.py:16
↓ 2 callersFunctiontl_gemm(
A,
B,
scales_a,
scales_b,
block_N,
in_dtype,
out_dtype,
accum_dtype,
)
examples/deepseek_deepgemm/example_deepgemm_fp8_2xAcc.py:12
↓ 2 callersFunctiontl_matmul_streamk(
A,
B,
C,
streamk_tiles,
block_M,
block_N,
block_K,
trans_A,
trans_B,
examples/gemm_streamk/example_tilelang_gemm_streamk.py:58
↓ 2 callersFunctiontorch_chunk_gated_delta_rule_bwd_dhu(
Q: torch.Tensor,
K: torch.Tensor,
W: torch.Tensor,
G: torch.Tensor,
h0: torch.Tensor,
examples/gdn/example_chunk_delta_bwd.py:108
↓ 1 callersFunctionMMA0(
K: T.Tensor(shape, dtype),
Q_shared: T.SharedBuffer([block_M, dim], dtype),
benchmark/blocksparse_attention/benchmark_tilelang_block_sparse_fmha.py:49
↓ 1 callersFunctionMMA0(
K: T.Tensor(shape, dtype),
Q_shared: T.Tensor([block_M, dim], dtype),
K_
testing/python/transform/test_tilelang_transform_config_index_bitwidth.py:28
↓ 1 callersFunctionMMA1(
V: T.Tensor(shape, dtype),
V_shared: T.SharedBuffer([block_M, dim], dtype),
benchmark/blocksparse_attention/benchmark_tilelang_block_sparse_fmha.py:68
↓ 1 callersFunctionMMA1(
V: T.Tensor(shape, dtype),
V_shared: T.Tensor([block_M, dim], dtype),
ac
testing/python/transform/test_tilelang_transform_config_index_bitwidth.py:47
↓ 1 callersFunction_blockscaled_gemm_ref(a, b, sfa_packed, sfb_packed, *, sf_granularity_k=128, transpose_B=False)
maint/gemm/correctness_evaluation_tcgen05_fp4_unpacked.py:267
↓ 1 callersFunction_build_autotuner(
M: int,
N: int,
K: int,
with_roller: bool,
profile_backend: str,
execution_backend:
examples/gemm/example_gemm_advanced_autotune.py:161