↓ 1 callersFunctionmqa_attn_return_logits(
IndexQ,
IndexK,
IndexKScale,
Weights,
CuSeqLenKS,
CuSeqLenKE,
block_N=256,
n
examples/deepseek_v32/fp8_lighting_indexer.py:90
↓ 1 callersFunctionnaive_nsa_simple_inferencer""" Args: q (torch.Tensor): queries of shape `[B, 1, HQ, K]` if `head_first=False` else `[B, HQ, T, K]`. k (torch.Ten
examples/deepseek_nsa/reference.py:230
↓ 1 callersFunctionnative_sparse_attention_varlen(
Q,
K,
V,
O_slc,
BlockIndices,
BlockCounts,
Offsets,
TokenIndices,
batch,
examples/deepseek_nsa/example_tilelang_nsa_fwd_varlen.py:26
↓ 1 callersFunctionparallel_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/example_triton_nsa_fwd_varlen.py:254
↓ 1 callersFunctionparallel_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/example_tilelang_nsa_fwd_varlen.py:227
↓ 1 callersFunctionparallel_nsar""" Args: q (torch.Tensor): queries of shape `[B, SEQLEN, HQ, K]` if `head_first=False` else `[B, HQ, SEQLEN, K]`. k
examples/deepseek_nsa/example_tilelang_nsa_bwd.py:702
↓ 1 callersFunctionparallel_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/example_triton_nsa_bwd.py:872
↓ 1 callersFunctionparallel_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/example_triton_nsa_fwd.py:235
↓ 1 callersFunctionpointer_table_grouped_matmul_test(batch_sizes_list, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_ptr.py:70
↓ 1 callersFunctionpool_mqa_attn_return_logits_fp8(
IndexQ,
IndexBlockedK,
IndexBlockedKScale,
Logits,
Weights,
CuSeqLenBlockedKS,
C
examples/dsa_hisa/pool_mqa_fp8.py:31
↓ 1 callersFunctionpostprocess(
dKV,
D,
D_tail,
kv_group=1,
block_N=64,
threads=128,
dtype=T.bfloat16,
accum
examples/deepseek_v32/sparse_mla_bwd.py:44
↓ 1 callersFunctionpostprocess(
dKV,
D,
D_tail,
kv_group=1,
block_N=64,
threads=128,
dtype=T.bfloat16,
accum
examples/dsa_sparse_finetune/sparse_mla_bwd.py:49
↓ 1 callersFunctionprepare_input(B, S, H, DK, DV, chunk_size, input_dtype, output_dtype, gate_dtype=torch.float32)
examples/gdn/example_wy_fast.py:24
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_wy_fast_bwd_split.py:51
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_delta_h.py:39
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_o.py:24
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_o_bwd.py:55
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
input_dtype,
output_dtype,
accum_dtype,
)
examples/gdn/example_chunk_scaled_dot_kkt.py:25
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
chunk_size,
sub_chunk_size,
input_dtype,
output_dtype,
accu
examples/kda/chunk_inter_solve_fused.py:15
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
gate_dt
examples/kda/chunk_intra_token_parallel.py:13
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/wy_fast_bwd.py:17
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_delta_bwd.py:16
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_delta_h_fwd.py:23
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
gate_dtype,
)
examples/kda/chunk_bwd_dqkwg.py:13
↓ 1 callersFunctionprepare_input(B, S, H, DK, DV, chunk_size, input_dtype, output_dtype, gate_dtype=torch.float32)
examples/kda/wy_fast.py:14
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_o.py:13
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
gate_dt
examples/kda/chunk_bwd_intra.py:16
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DV,
chunk_size,
input_dtype,
do_dtype,
)
examples/kda/chunk_bwd_gla_dA.py:13
↓ 1 callersFunctionprepare_input(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
do_dtype,
)
examples/kda/chunk_bwd_dv.py:14
↓ 1 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
gate_dtype,
state_dtype,
)
examples/kda/wy_fast_bwd.py:44
↓ 1 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
gate_dtype,
state_dtype,
)
examples/kda/chunk_delta_bwd.py:46
↓ 1 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
gate_dtype,
)
examples/kda/chunk_bwd_dqkwg.py:37
↓ 1 callersFunctionprepare_output(
B,
S,
H,
DK,
chunk_size,
NK,
output_dtype,
gate_dtype,
state_dtype,
)
examples/kda/chunk_bwd_intra.py:48