↓ 1 callersFunctionfused_chunkr""" Args: q (torch.Tensor): queries of shape `[B, T, H, K]`. k (torch.Tensor): keys of shape `[B, T, H, K
fla/ops/common/fused_chunk.py:590
↓ 1 callersFunctionfused_chunk_bwd(
q,
k,
v,
g,
g_gamma,
do,
scale,
initial_state: torch.Tensor,
dht: torch.
fla/ops/common/fused_chunk.py:458
↓ 1 callersFunctionfused_chunk_ttt_linearr""" Args: q (torch.Tensor): queries of shape `[B, T, H, K]`. k (torch.Tensor): keys of shape `[B, T, H, K
fla/ops/ttt/fused_chunk.py:732
↓ 1 callersFunctionfused_chunk_ttt_linear_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
b: torch.Tensor,
fla/ops/ttt/fused_chunk.py:608
↓ 1 callersFunctionfused_chunk_ttt_linear_bwd_dh(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
v2: torch.Tensor,
x: torch.Tensor,
fla/ops/ttt/fused_chunk.py:484
↓ 1 callersFunctionfused_chunk_ttt_linear_bwd_h(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
b: torch.Tensor,
fla/ops/ttt/fused_chunk.py:426
↓ 1 callersFunctionfused_chunk_ttt_linear_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
b: torch.Tensor,
fla/ops/ttt/fused_chunk.py:557
↓ 1 callersFunctionfused_grpo_loss_npu(
logits,
ref_logp,
input_ids,
advantages,
beta=0.1,
completion_mask=None,
save_kl
fla/modules/backends/triton_ascend/grpo.py:240
↓ 1 callersFunctionfused_recurrent_comba_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
p: torch.Tensor,
g: torch.Tensor,
fla/ops/comba/fused_recurrent.py:121
↓ 1 callersFunctionfused_recurrent_delta_rule_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
beta: torch.Tensor,
scale: float,
fla/ops/delta_rule/fused_recurrent.py:256
↓ 1 callersFunctionfused_recurrent_dplr_delta_rule_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
a: torch.Tensor,
b: torch.Tensor,
fla/ops/generalized_delta_rule/dplr/fused_recurrent.py:111
↓ 1 callersFunctionfused_recurrent_gdn2_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
b: torch.Tensor,
fla/ops/gdn2/fused_recurrent.py:252
↓ 1 callersFunctionfused_recurrent_gsa_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
s: torch.Tensor,
g: torch.Tensor,
fla/ops/gsa/fused_recurrent.py:232
↓ 1 callersFunctionfused_recurrent_gsa_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
s: torch.Tensor,
g: torch.Tensor,
fla/ops/gsa/fused_recurrent.py:139
↓ 1 callersFunctionfused_recurrent_gsa_inference(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
s: torch.Tensor,
g: torch.Tensor,
fla/ops/gsa/fused_recurrent.py:88
↓ 1 callersFunctionfused_recurrent_rwkv4_backward(
w: Tensor,
u: Tensor,
k: Tensor,
v: Tensor,
state: Tensor,
grad_wkv: Tensor,
gra
fla/ops/rwkv4/fused_recurrent.py:361
↓ 1 callersFunctionfused_recurrent_rwkv6_bwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
u: torch.Tensor,
fla/ops/rwkv6/fused_recurrent.py:402
↓ 1 callersFunctionfused_recurrent_rwkv6_fwd(
q: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
w: torch.Tensor,
u: torch.Tensor,
fla/ops/rwkv6/fused_recurrent.py:356
↓ 1 callersFunctionfused_recurrent_rwkv7_fwd(
r: torch.Tensor,
w: torch.Tensor,
k: torch.Tensor,
v: torch.Tensor,
kk: torch.Tensor,
fla/ops/rwkv7/fused_recurrent.py:133
↓ 1 callersFunctiongate_output_correction_backward_triton(grad_output, o, r, k, r_k, v, g)
fla/ops/rwkv7/gate_output_correction.py:185
↓ 1 callersFunctiongate_output_correction_ref o: [B, T, H*D] r: [B, T, H, D] k: [B, T, H, D] r_k: [H, D] v: [B, T, H, D] g: [B, T, H*D]
fla/ops/rwkv7/gate_output_correction.py:15