↓ 1 callersFunctiontest_sparse_mla_fwd_pipelined(
B=1, S=4096, SKV=8192, H=128, HKV=1, DQK=576, DV=512, topk=2048, dtype=torch.bfloat16, q_start_s_index=1
examples/deepseek_v32/sparse_mla_fwd_pipelined.py:421
↓ 1 callersFunctiontile_atomic_add_program(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:321
↓ 1 callersFunctiontile_atomic_max_program(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:525
↓ 1 callersFunctiontile_atomic_min_program(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:556
↓ 1 callersFunctiontilelang_chunk_bwd_intra(
# task config
B,
S,
H,
DK,
input_dtype,
output_dtype,
accum_dtype,
gate_
examples/kda/chunk_bwd_intra.py:81
↓ 1 callersFunctiontilelang_chunk_bwd_kernel_dv_local(
B,
S,
H,
DV,
scale,
input_dtype,
da_dtype,
do_dtype,
chunk_size,
blo
examples/kda/chunk_bwd_gla_dA.py:52
↓ 1 callersFunctiontilelang_chunk_bwd_kernel_dv_local(
B,
S,
H,
DV,
input_dtype,
output_dtype,
do_dtype,
chunk_size,
block_DV=1
examples/kda/chunk_bwd_dv.py:56
↓ 1 callersFunctiontilelang_chunk_fwd_o(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_o.py:62
↓ 1 callersFunctiontilelang_chunk_gated_delta_rule_bwd_dhu(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_delta_bwd.py:78
↓ 1 callersFunctiontilelang_chunk_gated_delta_rule_fwd_h(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_delta_h_fwd.py:80
↓ 1 callersFunctiontilelang_chunk_kda_fwd_inter_fused(
B,
S,
H,
DK,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
chunk_s
examples/kda/chunk_inter_solve_fused.py:53
↓ 1 callersFunctiontilelang_chunk_kda_fwd_intra_token_parallel(
B,
S,
H,
DK,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
chunk_s
examples/kda/chunk_intra_token_parallel.py:60
↓ 1 callersFunctiontilelang_copy(M, N, block_M, block_N, dtype=T.float16, pad_value=0)
testing/python/language/test_tilelang_language_annotate_safe_value.py:9
↓ 1 callersFunctiontilelang_copy_with_stride(M, N, NN, block_M, block_N, dtype=T.float16)
testing/python/language/test_tilelang_language_copy.py:47
↓ 1 callersFunctiontilelang_kernel_bwd_dqkv(
Q,
K,
V,
LSE_slc,
Delta_slc,
DO_slc,
DQ,
DK,
DV,
BlockMask,
dim,
examples/deepseek_nsa/example_tilelang_nsa_bwd.py:319
↓ 1 callersFunctiontilelang_kernel_fwd(
Q,
K,
V,
BlockIndices,
dim,
is_causal,
scale=None,
block_size=64,
groups
examples/deepseek_nsa/example_tilelang_nsa_bwd.py:23
↓ 1 callersFunctiontilelang_kernel_preprocess(
O,
dO,
dtype=T.float16,
accum_dtype=T.float32,
blk=32,
)
examples/deepseek_nsa/example_tilelang_nsa_bwd.py:481
↓ 1 callersFunctiontilelang_recompute_w_u_fwd(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
gate_dtype,
examples/kda/wy_fast.py:55
↓ 1 callersFunctiontilelang_transposeKernel: read tile from A into shared, transpose in shared, write to B. A is (M, N), B is (M, N). B = A.T.T = A when block_M == M and block_N
testing/python/language/test_tilelang_language_transpose.py:9
↓ 1 callersFunctiontilelang_wy_fast_bwd(
# task config
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/wy_fast_bwd.py:81
↓ 1 callersFunctiontl_indexer_bwd_impl(
IndexQ,
Weights,
IndexK,
AttnScore,
IndexScore,
TopkIndices,
Offsets,
TokenI
examples/dsa_sparse_finetune/indexer_bwd.py:20
↓ 1 callersFunctiontl_indexer_topk_reducesum_impl(
heads: int,
dim: int,
topk: int,
sm_scale: Optional[float] = None,
block_K: int = 32,
examples/dsa_sparse_finetune/indexer_topk_reducesum.py:21
↓ 1 callersFunctiontl_matmul(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
)
examples/bitnet-1.58b/kernel_benchmark/tl_int8xint8.py:32
↓ 1 callersFunctiontl_matmul(
M,
N,
K,
block_M,
block_N,
block_K,
num_stages,
k_pack=2,
num_threads=25
examples/gemm_fp8/example_tilelang_gemm_amd_fp8_preshuffle.py:39
↓ 1 callersFunctiontl_matmulBuild a TileLang MFMA kernel for ``A @ B^T`` (with optional preshuffle). The (block_*_warps, warp_*_tiles, chunk, num_stages, panel_size) paramet
testing/python/amd/test_tilelang_gemm_mfma_preshuffle.py:16
↓ 1 callersFunctiontl_matmul(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
a_transposed=False,
b_transposed=
testing/python/amd/test_tilelang_gemm_mfma_intrinsic.py:17
↓ 1 callersFunctiontl_matmul_simt(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
)
testing/python/kernel/test_tilelang_kernel_gemm_simt.py:29
↓ 1 callersFunctiontl_matmul_with_ladder_weight_only_transform_block_reduce_int4(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
transform_b,
)
examples/dequantize_gemm/example_dequant_gemm_fine_grained.py:137
↓ 1 callersFunctiontl_sparse_mla_topk_reducesum_impl(
Q,
KV,
Indices,
Lse,
Offsets,
TokenIndices,
heads,
dim,
tail_dim,
to
examples/dsa_sparse_finetune/sparse_mla_topk_reducesum.py:19
↓ 1 callersFunctiontl_topk_impl(input, index, starts, ends, in_dtype=T.float32, out_dtype=T.int32)
examples/deepseek_v32/topk_selector.py:28