↓ 1 callersFunctionintra_chunk_preprocess_bwd_fn(q, k, w, w2, beta,
dq, dk, dA_local,
dw1,
fla/ops/path_attn/intra_chunk_preprocess_bwd.py:121
↓ 1 callersFunctionintra_chunk_preprocess_bwd_prepare_fn(q, k, v, w, beta, g_cumsum, A, L, D, do, scale, return_h=True, cu_seqlens=None,
fla/ops/path_attn/intra_chunk_preprocess_bwd_prepare.py:153
↓ 1 callersFunctionintra_chunk_preprocess_fwd_fn(q, k, v, w, beta, g_cumsum, A, scale, BT, cu_seqlens,
chunk_indices: torch.
fla/ops/path_attn/intra_chunk_preprocess_fwd.py:132
↓ 1 callersFunctionlayer_norm_bwd(
dy: torch.Tensor,
x: torch.Tensor,
weight: torch.Tensor,
bias: torch.Tensor,
eps: float,
fla/modules/fused_bitlinear.py:319
↓ 1 callersFunctionlayer_norm_bwd(
dy: torch.Tensor,
x: torch.Tensor,
weight: torch.Tensor,
bias: torch.Tensor,
eps: float,
fla/modules/layernorm_gated.py:303
↓ 1 callersFunctionlayernorm_fn(x, weight, bias, z=None, eps=1e-6, group_size=None, norm_before_gate=True, is_rms_norm=False)
fla/modules/layernorm_gated.py:462
↓ 1 callersFunctionnaive_mesa_net_decoding_one_step(q, k, v, g, lamb, beta, prev_h_kk, prev_h_kv, max_CG_iteration=30)
fla/ops/mesa_net/naive.py:12
↓ 1 callersFunctionparallel_attn_bwd_tilelang(
q, k, v, o, g_cumsum, lse, do,
sink_bias=None, scale=None, window_size=None,
chunk_size=128, cu_
fla/ops/common/backends/tilelang/parallel_attn_bwd.py:237
↓ 1 callersFunctionparallel_deltaformer_kernel(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
u: torch.Tensor,
w: torch.Tensor,
fla/ops/deltaformer/parallel.py:103
↓ 1 callersFunctionparallel_nsa_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
o: torch.Tensor,
lse: torch.Tensor,
fla/ops/nsa/parallel.py:628
↓ 1 callersFunctionparallel_nsa_compression_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
o: torch.Tensor,
lse: torch.Tensor,
fla/ops/nsa/compression.py:378
↓ 1 callersFunctionparallel_nsa_compression_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
block_size: int,
scale: float,
cu
fla/ops/nsa/compression.py:325
↓ 1 callersFunctionparallel_parallax_fwdParallax forward (Triton). `(B, T, HQ, D)` / packed `(1, T_total, HQ, D)` inputs. Returns `(o, barv, d1, bart, m)`: `o`/`barv` in the input dtype
fla/ops/parallax/parallel.py:645
↓ 1 callersFunctionparallel_path_bwd_dkv_fn(
q, k, v, g_cumsum, do, dv, dg_cumsum,
hc_whole, scale, L, D,
cu_seqlens,
S, BT, BS,
chun
fla/ops/path_attn/parallel_path_bwd_inter_dkv.py:146
↓ 1 callersFunctionparallel_path_bwd_dq_fn(
q,
k,
v,
g_cumsum,
do,
dg_cumsum,
hc_whole,
scale,
L,
D,
cu_seql
fla/ops/path_attn/parallel_path_bwd_inter_dqh.py:142
↓ 1 callersFunctionparallel_path_bwd_intra_chunk_fn(
q, k, v, g_cumsum, w1, w2,
dq, dk, dv, dg_cumsum, dw1, dw2, do,
scale, L, D,
cu_seqlens,
fla/ops/path_attn/parallel_path_bwd_intra.py:152
↓ 1 callersFunctionparallel_path_fwd_fn(
q,
k,
v,
o,
g_cumsum,
w1,
w2,
scale,
L,
M,
cu_seqlens,
BT,
fla/ops/path_attn/parallel_path_fwd.py:150
↓ 1 callersFunctionparallel_simple_gla_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
do: torch.Tensor,
fla/ops/simple_gla/parallel.py:553
↓ 1 callersFunctionparallel_simple_gla_bwd_kernel_dkv(
i_t,
i_k,
i_v,
q,
k,
v,
g,
do,
dk,
dv,
dg,
scale,
T,
fla/ops/simple_gla/parallel.py:257
↓ 1 callersFunctionparallel_simple_gla_bwd_kernel_dq(
i_t,
i_k,
i_v,
q,
k,
v,
g,
do,
dq,
dg,
scale,
T,
H: tl.c
fla/ops/simple_gla/parallel.py:166
↓ 1 callersFunctionparallel_simple_gla_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
scale: float,
ou
fla/ops/simple_gla/parallel.py:482
↓ 1 callersFunctionprepare_k_cache_fn(k, w1, w2, cu_seqlens, BS, use_cache=False, chunk_indices: torch.LongTensor | None = None)
fla/ops/path_attn/prepare_k_cache.py:59
↓ 1 callersFunctionprepare_wy_repr_bwd(
k: torch.Tensor,
v: torch.Tensor,
beta: torch.Tensor,
A: torch.Tensor,
dw: torch.Tensor,
fla/ops/gated_delta_rule/wy_fast.py:269