↓ 1 callersFunctionchunk_generalized_iplr_delta_rule_fwd_o(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
v_new: torch.Tensor,
b: torch.Tensor,
fla/ops/generalized_delta_rule/iplr/chunk.py:208
↓ 1 callersFunctionchunk_gla_bwd_dqkg(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
h: torch.Tensor,
g: torch.Tensor,
fla/ops/gla/chunk.py:1042
↓ 1 callersFunctionchunk_iplr_delta_ruler""" Args: q (torch.Tensor): queries of shape `[B, T, H, K]`. k (torch.Tensor): keys of shape `[B, T, H, K
fla/ops/generalized_delta_rule/iplr/chunk.py:430
↓ 1 callersFunctionchunk_kda_bwd_wy_dqkg_fused(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
v_new: torch.Tensor,
g: torch.Tensor,
fla/ops/kda/chunk_bwd.py:352
↓ 1 callersFunctionchunk_kda_bwd_wy_dqkg_fused_tilelang(
q, k, v, v_new, g, beta, A, h, do, dh, dv,
scale=None, cu_seqlens=None, chunk_size=64,
chunk_ind
fla/ops/kda/backends/tilelang/chunk_bwd_dqkg.py:419
↓ 1 callersFunctionchunk_kda_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
beta: torch.Tensor,
fla/ops/kda/chunk_fwd.py:20
↓ 1 callersFunctionchunk_mesa_cg_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
h: torch.Tensor,
h_kv: torch.Tensor,
fla/ops/mesa_net/chunk_cg_solver_fwd.py:137
↓ 1 callersFunctionchunk_mesa_net_h_kk_bwd_intra_fn(
k: torch.Tensor,
beta: torch.Tensor,
g: torch.Tensor,
h: torch.Tensor,
dh: torch.Tensor,
fla/ops/mesa_net/chunk_h_kk_intra_bwd.py:140
↓ 1 callersFunctionchunk_mesa_net_h_kv_bwd_intra_fn(
q_star,
k,
v,
beta,
h_kv,
dh_kv,
g,
do,
cu_seqlens,
chunk_size=64,
fla/ops/mesa_net/chunk_h_kv_intra_bwd.py:152
↓ 1 callersFunctionchunk_mesa_net_h_kv_bwd_intra_separate_fn(
q_star,
k,
v,
beta,
h_kv,
dh_kv,
g,
do,
cu_seqlens,
chunk_size=64,
fla/ops/mesa_net/chunk_h_kv_intra_bwd_separate.py:236
↓ 1 callersFunctionchunk_oja_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
gv: torch.Tensor,
beta: torch.Tensor,
fla/ops/gated_oja_rule/chunk.py:86
↓ 1 callersFunctionchunk_oja_bwd_dhu(
q: torch.Tensor,
vg: torch.Tensor,
w: torch.Tensor,
do: torch.Tensor,
dk: torch.Tensor,
fla/ops/gated_oja_rule/chunk_h.py:462
↓ 1 callersFunctionchunk_oja_bwd_dqk(
q: torch.Tensor,
k: torch.Tensor,
h: torch.Tensor,
gv: torch.Tensor,
dA: torch.Tensor,
fla/ops/gated_oja_rule/chunk_o.py:484
↓ 1 callersFunctionchunk_oja_bwd_dv_o(
v: torch.Tensor,
gv: torch.Tensor,
o: torch.Tensor,
A: torch.Tensor,
dv: torch.Tensor,
fla/ops/gated_oja_rule/chunk_o.py:634
↓ 1 callersFunctionchunk_oja_bwd_dvwg_h(
k: torch.Tensor,
v: torch.Tensor,
h: torch.Tensor,
dh: torch.Tensor,
dk: torch.Tensor,
fla/ops/gated_oja_rule/chunk_h.py:764
↓ 1 callersFunctionchunk_oja_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
gv: torch.Tensor,
beta: torch.Tensor,
fla/ops/gated_oja_rule/chunk.py:25
↓ 1 callersFunctionchunk_oja_fwd_o(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
gv: torch.Tensor,
h: torch.Tensor,
fla/ops/gated_oja_rule/chunk_o.py:184
↓ 1 callersFunctionchunk_rwkv6_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
u: torch.Tensor,
fla/ops/rwkv6/chunk.py:1073
↓ 1 callersFunctionchunk_rwkv6_bwd_dh(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
gi: torch.Tensor,
ge: torch.Tensor,
fla/ops/rwkv6/chunk.py:855
↓ 1 callersFunctionchunk_rwkv6_bwd_dqk_intra(
q: torch.Tensor,
k: torch.Tensor,
gi: torch.Tensor,
ge: torch.Tensor,
dA: torch.Tensor,
fla/ops/rwkv6/chunk.py:908
↓ 1 callersFunctionchunk_rwkv6_bwd_dqkgu(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
h: torch.Tensor,
g: torch.Tensor,
fla/ops/rwkv6/chunk.py:953
↓ 1 callersFunctionchunk_rwkv6_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
u: torch.Tensor,
fla/ops/rwkv6/chunk.py:1014
↓ 1 callersFunctionchunk_rwkv6_fwd_intra(
q: torch.Tensor,
k: torch.Tensor,
gi: torch.Tensor,
ge: torch.Tensor,
u: torch.Tensor,
fla/ops/rwkv6/chunk.py:752
↓ 1 callersFunctionchunk_rwkv7 Args: r (torch.Tensor): r of shape `[B, T, H, K]`. w (torch.Tensor): log decay of shape `[B, T, H, K]`.
fla/ops/rwkv7/chunk.py:13
↓ 1 callersFunctionchunk_titans_linear(
q, k, v, w, b, theta, alpha, eta, eps, chunk_size, initial_state, output_final_state,
)
fla/ops/titans/naive.py:216
↓ 1 callersFunctionchunk_transform_qk_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
beta: torch.Tensor,
A: torch.Tensor,
fla/ops/delta_rule/parallel.py:85
↓ 1 callersFunctionchunk_ttt_linear_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
b: torch.Tensor,
fla/ops/ttt/chunk.py:1205
↓ 1 callersFunctionchunk_ttt_linear_bwd_dqke(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
eta: torch.Tensor,
h: torch.Tensor,
fla/ops/ttt/chunk.py:1101
↓ 1 callersFunctionchunk_ttt_linear_bwd_norm(
q: torch.Tensor, # [B, H, L, D]
k: torch.Tensor, # [B, H, L, D]
v: torch.Tensor, # [B, H, L,
fla/ops/ttt/chunk.py:904
↓ 1 callersFunctionchunk_ttt_linear_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
b: torch.Tensor,
fla/ops/ttt/chunk.py:1159
↓ 1 callersFunctionchunk_update_once(
b_p,
b_k,
b_v,
b_m,
b_g_exp_q,
b_h,
b_lamb,
)
fla/ops/mesa_net/chunk_cg_solver_bwd.py:17
↓ 1 callersFunctioncompute_x_k_grad Args: dk1: (batch*seq_len, hidden_dim) x: (batch, seq_len, hidden_dim) x_prev: (batch, hidden_dim) or (batch, 1, hidden_d
fla/ops/rwkv7/channel_mixing.py:249
↓ 1 callersFunctiondplr_recurrence(q, k, v, alpha, beta, gk, initial_state=None, output_final_state=True)
fla/ops/generalized_delta_rule/dplr/naive.py:16