Functionchunkwise_fwd_kernel(
q,
k,
v,
g,
level_scales,
llut,
o,
h0,
ht,
offsets,
new_offsets,
fla/ops/log_linear_attn/chunk.py:42
Functioncompute_dh0_kernel(
dy,
y,
weight,
dh0,
cu_seqlens,
stride_dy_n,
stride_dy_t,
stride_dy_d,
s
fla/modules/backends/triton_ascend/causal_conv1d.py:528
Methodcompute_dh0_triton(
self,
dy,
y,
weight,
initial_state,
activation,
cu_s
fla/modules/backends/triton_ascend/__init__.py:341
Functioncopy_input_kernel(
q,
k,
v,
g,
level_scales,
cu_seqlens,
q_prev,
k_prev,
v_prev,
g_prev
fla/ops/log_linear_attn/chunk.py:678
Functioncopy_last_chunk_kernel(
q,
k,
v,
g,
level_scales,
cu_seqlens,
q_prev,
k_prev,
v_prev,
g_prev
fla/ops/log_linear_attn/chunk.py:829
Functioncross_entropy_bwd_kernel(
dlogits_ptr, # data ptrs
dloss_ptr,
logits_ptr,
lse_ptr,
labels_ptr,
label_smoothin
fla/modules/fused_cross_entropy.py:108
Functioncross_entropy_bwd_kernel(
dlogits_ptr,
dloss_ptr,
logits_ptr,
lse_ptr,
labels_ptr,
label_smoothing,
logit_
fla/modules/backends/triton_ascend/fused_cross_entropy.py:96
Functioncross_entropy_fwd_kernel(
loss_ptr, # data ptrs
lse_ptr,
z_loss_ptr,
logits_ptr,
labels_ptr,
label_smoothing,
fla/modules/fused_cross_entropy.py:32
Functioncross_entropy_fwd_kernel(
loss_ptr,
lse_ptr,
z_loss_ptr,
logits_ptr,
labels_ptr,
label_smoothing,
logit_sc
fla/modules/backends/triton_ascend/fused_cross_entropy.py:23
Functioncross_entropy_kernel(
logits,
lse,
target,
loss,
total,
ignore_index,
label_smoothing: tl.constexpr,
fla/modules/backends/triton_ascend/fused_linear_cross_entropy.py:70
Methodcross_entropy_loss(
self,
logits,
target,
label_smoothing=0.0,
logit_scale=1.0,
fla/modules/backends/triton_ascend/__init__.py:53
Functiondplr_chunkwise(q, k, v, alpha, beta, gk, initial_state=None, output_final_state=True, chunk_size=32)
fla/ops/generalized_delta_rule/dplr/naive.py:41
Methodforward(
ctx,
q,
k,
v,
self_attn_cu_seqlens,
moba_q,
moba_kv,
fla/ops/moba/parallel.py:109
Methodforward(ctx, o, q, k, scale, z_init, reverse, cu_seqlens)
fla/ops/linear_attn/utils.py:21
Methodforward(
ctx,
q,
k,
v,
g,
beta,
lamb,
cu_seqlens,
fla/ops/mesa_net/chunk.py:189
Methodforward(ctx, o, r, k, r_k, v, g)
fla/ops/rwkv7/gate_output_correction.py:221
Methodforward(
ctx, hidden_states, delta,
x_r, x_w, x_k, x_v, x_a, x_g,
)
fla/ops/rwkv7/fused_addcmul.py:223
Methodforward(ctx, x, x_prev, x_k, key_weight, value_weight, inplace: bool = True)
fla/ops/rwkv7/channel_mixing.py:307
Methodforward(ctx, q, k, v, g, sink_bias, scale, window_size, cu_seqlens, g_scalar=None, chunk_indices=None)
fla/ops/wall_attn/parallel.py:814
Methodforward(ctx, q, k, v, w, beta, g, scale, cu_seqlens, use_cache=False)
fla/ops/path_attn/parallel.py:33
Methodforward(ctx, q, k, v, g, sink_bias, scale, window_size, cu_seqlens, chunk_indices=None)
fla/ops/attn/parallel.py:725
Methodforward(ctx, q, r, k, v, scale, window_size_left, cu_seqlens)
fla/ops/parallax/parallel.py:728
Methodforward(
ctx,
q,
k,
v,
g,
u,
scale,
initial_state,
fla/ops/rwkv6/chunk.py:1177
Methodforward(
ctx,
q,
k,
v,
g,
g_gamma,
scale,
initial_sta
fla/ops/common/fused_chunk.py:524
Methodforward(
ctx,
q,
k,
v,
g,
scale,
initial_state,
outpu
fla/ops/gla/chunk.py:1266
Methodforward(ctx, q, k, v, block_indices, block_counts, block_size, scale, cu_seqlens)
fla/ops/nsa/parallel.py:730
Methodforward(
ctx,
q,
k,
v,
block_size,
scale,
cu_seqlens,
)
fla/ops/nsa/compression.py:477
Methodforward(ctx, q, k, v, beta, scale, output_attentions)
fla/ops/delta_rule/parallel.py:242
Methodforward(ctx, q, k, v, w, b, BT, eta, scale, eps, initial_state,
initial_state_bias, output_final_stat
fla/ops/ttt/fused_chunk.py:670
Methodforward(
ctx,
q,
k,
v,
w,
b,
chunk_size,
eta,
fla/ops/ttt/chunk.py:1293
Methodforward(
ctx,
q,
k,
v,
g,
level_scales,
initial_state,
fla/ops/log_linear_attn/chunk.py:1516
Methodforward(ctx, q, k, v, g, scale, output_attentions, cu_seqlens, cu_seqlens_cpu)
fla/ops/simple_gla/parallel.py:628
Methodforward(
ctx,
q,
k,
v,
g,
g_gamma,
scale,
initial_sta
fla/ops/simple_gla/chunk.py:145
Methodforward(
ctx,
x,
norm_weight,
norm_bias,
linear_weight,
linear_bias,
fla/modules/layernorm.py:1144
Methodforward(self, x, weight, bias, residual=None, prenorm=False, residual_in_fp32=False)
fla/modules/layernorm.py:1286
Methodforward(self, x, weight, bias, residual=None, prenorm=False, residual_in_fp32=False)
fla/modules/layernorm.py:1351
Methodforward(self, x, weight, bias, residual=None, prenorm=False, residual_in_fp32=False)
fla/modules/layernorm.py:1408