↓ 12 callersFunctionassert_stable_rel(
ours: Tensor,
ref: Tensor,
*,
label: str,
cfg: str,
rel_tol: float = REL_TOL,
)
tests/ops/tilelang/test_mamba3_mimo.py:94
↓ 8 callersFunctionmamba3_MIMO_chunk_ref(
q: Tensor,
k: Tensor,
v: Tensor,
q_bias: Tensor,
k_bias: Tensor,
mimo_v: Tensor,
tests/ops/tilelang/test_mamba3_mimo.py:464
↓ 6 callersFunctionselective_state_update Argument: state: (batch, dim, dstate) or (batch, nheads, dim, dstate) x: (batch, dim) or (batch, nheads, dim) dt: (batch,
mamba_ssm/ops/triton/selective_state_update.py:135
↓ 5 callersFunction_state_passing_fwd(states, dA_chunk_cumsum, initial_states=None, seq_idx=None, chunk_size=None,
out_dtype
mamba_ssm/ops/triton/ssd_state_passing.py:196
↓ 5 callersFunctionbuild_inputs(
*,
mods: SimpleNamespace,
n: int,
p: int,
r: int,
chunk_size: int,
seed: int,
tests/ops/tilelang/test_mamba3_mimo.py:123
↓ 5 callersMethodgenerate(
self,
input_ids,
max_length,
top_k=1,
top_p=0.0,
min_p=0.0,
mamba_ssm/utils/generation.py:250
↓ 4 callersFunction_bmm_chunk_bwd Argument: a: (batch, seqlen, k) or (batch, seqlen, ngroups, k) dout: (batch, nchunks, chunk_size, chunk_size) or (batch, nchunks,
mamba_ssm/ops/triton/ssd_bmm.py:213
↓ 4 callersFunction_chunk_cumsum_fwd(dt, A, chunk_size, dt_bias=None, dt_softplus=False, dt_limit=(0.0, float("inf")))
mamba_ssm/ops/triton/ssd_chunk_state.py:718
↓ 4 callersFunction_chunk_scan_bwd_dC(prev_states, dA_cumsum, dout, seq_idx=None, C=None, ngroups=1)
mamba_ssm/ops/triton/ssd_chunk_scan.py:1451
↓ 4 callersFunction_chunk_state_bwd_db(x, dt, dA_cumsum, dstates, seq_idx=None, B=None, ngroups=1)
mamba_ssm/ops/triton/ssd_chunk_state.py:902
↓ 4 callersFunction_chunk_state_fwd(B, x, dt, dA_cumsum, seq_idx=None, states=None, states_in_fp32=True)
mamba_ssm/ops/triton/ssd_chunk_state.py:812
↓ 4 callersFunctionmamba3_step_fn(
# B: batch size, H: num heads, D: head dim, N: dstate, R: mimo
state: Tensor, # (B, H, D, N) — upda
mamba_ssm/ops/cute/mamba3/mamba3_step_fn.py:566
↓ 4 callersFunctionselective_state_update_ref Argument: state: (batch, dim, dstate) or (batch, nheads, dim, dstate) x: (batch, dim) or (batch, nheads, dim) dt: (batch,
mamba_ssm/ops/triton/selective_state_update.py:224
↓ 3 callersFunction_assert_close(
actual: Tensor,
expected: Tensor,
*,
label: str,
cfg: str,
step: Optional[int] = Non
tests/ops/cute/test_mamba3_mimo_step.py:127
↓ 3 callersFunction_bmm_chunk_fwd Argument: a: (batch, seqlen, k) or (batch, seqlen, ngroups, k) b: (batch, seqlen, k) or (batch, seqlen, ngroups, k) seq_i
mamba_ssm/ops/triton/ssd_bmm.py:165
↓ 3 callersFunction_chunk_cumsum_bwd(ddA, ddt_out, dt, A, dt_bias=None, dt_softplus=False, dt_limit=(0.0, float("inf")), ddt=None)
mamba_ssm/ops/triton/ssd_chunk_state.py:744
↓ 3 callersFunction_chunk_scan_chunk_state_bwd_dx(x, dt, dA_cumsum, B, CB, dout, dstates, D=None, seq_idx=None, dx=None)
mamba_ssm/ops/triton/ssd_combined.py:262
↓ 3 callersFunction_layer_norm_fwd(
x,
weight,
bias,
eps,
residual=None,
x1=None,
weight1=None,
bias1=None,
mamba_ssm/ops/triton/layer_norm.py:291
↓ 3 callersFunction_mamba_chunk_scan_combined_bwd(dout, x, dt, A, B, C, out, chunk_size, D=None, z=None,
dt_bias=None, initi
mamba_ssm/ops/triton/ssd_combined.py:396
↓ 3 callersFunction_mamba_chunk_scan_combined_fwd(x, dt, A, B, C, chunk_size, D=None, z=None, dt_bias=None, initial_states=None, seq_idx=None, cu_seqlens=None,
mamba_ssm/ops/triton/ssd_combined.py:343
↓ 3 callersFunction_run_case_outputs(
*,
case: str,
deterministic: bool,
seed: int,
headdim: int = 64,
dstate: int = 64,
tests/test_determinism.py:85
↓ 3 callersFunctioncreate_mamba3_siso_inputs(
batch: int,
seqlen: int,
nheads: int,
nheads_qk: int,
headdim_qk: int,
headdim_v: in
tests/ops/triton/test_mamba3_siso.py:406
↓ 3 callersFunctionlayer_norm_fn(
x,
weight,
bias,
residual=None,
x1=None,
weight1=None,
bias1=None,
eps=1e-6,
mamba_ssm/ops/triton/layer_norm.py:888
↓ 3 callersFunctionmamba_chunk_scan_combined Argument: x: (batch, seqlen, nheads, headdim) dt: (batch, seqlen, nheads) A: (nheads) B: (batch, seqlen, ngroups,
mamba_ssm/ops/triton/ssd_combined.py:624
↓ 3 callersFunctionrun_case(B, R, N, D, RD, with_bias, conjugate, expanded_heads, rotate_pairwise)
mamba_ssm/ops/triton/mamba3/mamba3_mimo_rotary_step.py:335
↓ 2 callersFunction_chunk_scan_bwd_dcb(x, dt, dA_cumsum, dout, seq_idx=None, CB=None, ngroups=1)
mamba_ssm/ops/triton/ssd_chunk_scan.py:1514
↓ 2 callersFunction_chunk_scan_bwd_dz(x, z, out, dout, chunk_size, has_ddAcs=True, D=None, dz=None, recompute_output=False)
mamba_ssm/ops/triton/ssd_chunk_scan.py:1363
↓ 2 callersFunction_chunk_scan_fwd(cb, x, dt, dA_cumsum, C, states, D=None, z=None, seq_idx=None)
mamba_ssm/ops/triton/ssd_chunk_scan.py:1259
↓ 2 callersFunction_layer_norm_bwd(dy, x, weight, bias, eps, mean, rstd, z=None, group_size=None,
norm_before_gate=True, is_
mamba_ssm/ops/triton/layernorm_gated.py:271
↓ 2 callersFunction_layer_norm_bwd(
dy,
x,
weight,
bias,
eps,
mean,
rstd,
dresidual=None,
dy1=None,
weig
mamba_ssm/ops/triton/layer_norm.py:589
↓ 2 callersFunction_layer_norm_fwd(x, weight, bias, eps, z=None, out=None, group_size=None, norm_before_gate=True, is_rms_norm=False)
mamba_ssm/ops/triton/layernorm_gated.py:108
↓ 2 callersMethodallocate_inference_cache(self, batch_size, max_seqlen, device=None, dtype=None, inplace_state=None, **kwargs)
mamba_ssm/modules/mamba3.py:414
↓ 2 callersFunctionchunk_state Argument: B: (batch, seqlen, ngroups, dstate) x: (batch, seqlen, nheads, headdim) dt: (batch, nheads, nchunks, chunk_size
mamba_ssm/ops/triton/ssd_chunk_state.py:1081