Functiontest_parallel(
B: int,
T: int,
H: int,
D: int,
scale: float,
gate_logit_normalizer: float,
dtyp
tests/ops/test_simple_gla.py:618
Functiontest_parallel(
B: int,
T: int,
H: int,
HQ: int,
D: int,
scale: float,
dtype: torch.dtype,
)
tests/ops/test_parallax.py:51
Functiontest_parallel(
B: int,
T: int,
H: int,
HQ: int,
D: int,
scale: float,
)
tests/ops/test_forgetting_attn.py:29
Functiontest_parallel(
B: int,
T: int,
H: int,
K: int,
expand_ratio: int,
dtype: torch.dtype,
)
tests/ops/test_retention.py:283
Functiontest_parallel_matches_reference(B: int, T: int, H: int, HQ: int, K: int, V: int, window_size)
tests/ops/test_wall_attn.py:53
Functiontest_parallel_swa(
B: int,
T: int,
H: int,
HQ: int,
D: int,
W: int,
)
tests/ops/test_attn.py:221
Functiontest_parallel_swa(
B: int,
T: int,
H: int,
HQ: int,
D: int,
W: int,
dtype: torch.dtype,
)
tests/ops/test_parallax.py:107
Functiontest_parallel_swa(
B: int,
T: int,
H: int,
HQ: int,
D: int,
W: int,
)
tests/ops/test_forgetting_attn.py:148
Functiontest_parallel_swa_varlen(H: int, HQ: int, D: int, W: int, cu_seqlens: list[int], dtype: torch.dtype)
tests/ops/test_parallax.py:205
Functiontest_parallel_varlen(
H: int,
HQ: int,
D: int,
use_forget_gate: bool,
cu_seqlens: list[int],
dtype: torch.
tests/ops/test_path_attn.py:112
Functiontest_parallel_with_g(
B: int,
T: int,
H: int,
HQ: int,
D: int,
scale: float,
)
tests/ops/test_attn.py:113
Functiontest_powglu(B: int, T: int, D: int, power: float, noncontiguous: bool, compile: bool)
tests/modules/test_activation.py:310
Functiontest_powglu_linear(B: int, T: int, D: int, O: int, power: float, noncontiguous: bool, compile: bool)
tests/modules/test_activation.py:338
Functiontest_recurrent_fwd(
B: int,
T: int,
H: int,
D: int,
scale: float,
dtype: torch.dtype,
)
tests/ops/test_dplr_delta.py:150
Functiontest_sigmoidglu_linear(B: int, T: int, D: int, O: int, noncontiguous: bool, compile: bool)
tests/modules/test_activation.py:277
Functiontest_swiglu_linear(B: int, T: int, D: int, O: int, noncontiguous: bool, compile: bool)
tests/modules/test_activation.py:216
Functiontest_unpack_sequence(
B: int,
T: int,
H: int,
D: int,
padding_side: str,
dtype: torch.dtype,
)
tests/ops/utils/test_pack.py:73
Functiontoken_shift_bwd_kernel_long(
dx,
dy,
cu_seqlens,
chunk_indices,
grad_cache_in,
grad_cache_out,
T,
D: tl.c
fla/modules/token_shift.py:314
Functiontoken_shift_bwd_kernel_short(
dx,
dy,
cu_seqlens,
grad_cache_in,
grad_cache_out,
T,
D: tl.constexpr,
BD: t
fla/modules/token_shift.py:236
Functiontoken_shift_fwd_kernel_long(
x,
y,
cu_seqlens,
chunk_indices,
cache,
cache_out,
T,
D: tl.constexpr,
B
fla/modules/token_shift.py:160
Functiontoken_shift_fwd_kernel_short(
x,
y,
cu_seqlens,
cache,
cache_out,
T,
D: tl.constexpr,
BD: tl.constexpr,
fla/modules/token_shift.py:68
Functiontransform_q_fwd_kernel(
q,
q_new,
w1,
w2,
cu_seqlens,
indices,
T,
S: tl.constexpr,
G: tl.constex
fla/ops/path_attn/transform_q.py:19
Functionwu_fwd_kernel(
w,
u,
a,
k,
v,
A,
cu_seqlens,
chunk_indices,
T,
H: tl.constexpr,
fla/ops/generalized_delta_rule/iplr/wy_fast.py:166
Functionwu_fwd_kernel(
w,
u,
ag,
v,
A_ab_inv,
A_ak,
cu_seqlens,
chunk_indices,
T,
H: tl.con
fla/ops/generalized_delta_rule/dplr/wy_fast_fwd.py:156