↓ 1 callersFunctionrms_norm_fn(
x,
weight,
bias,
residual=None,
x1=None,
weight1=None,
bias1=None,
eps=1e-6,
mamba_ssm/ops/triton/layer_norm.py:922
↓ 1 callersFunctionssd_minimal_discrete Arguments: X: (batch, length, n_heads, d_head) A: (batch, length, n_heads) B: (batch, length, n_heads, d_state) C
mamba_ssm/modules/ssd_minimal.py:34
↓ 1 callersFunctionstate_passing Argument: states: (batch, nchunks, nheads, dim) dA_chunk_cumsum: (batch, nheads, nchunks) initial_states: (batch, nheads,
mamba_ssm/ops/triton/ssd_state_passing.py:314
↓ 1 callersFunctionstate_passing_ref Argument: states: (batch, nchunks, nheads, dim) dA_chunk_cumsum: (batch, nheads, nchunks) initial_states: (batch, nheads,
mamba_ssm/ops/triton/ssd_state_passing.py:327
↓ 1 callersFunctionupdate_graph_cache(
model,
cache,
batch_size,
seqlen_og,
max_seqlen,
decoding_seqlens=(1,),
dtype=No
mamba_ssm/utils/generation.py:283
Method__call__(
# B: batch size, H: num heads, D: head dim, N: dstate, R: mimo
self,
mState: cute.Te
mamba_ssm/ops/cute/mamba3/mamba3_step_fn.py:86
Method__init__(self, pretrained="state-spaces/mamba-2.8b", max_length=2048, batch_size=None, device="cuda",
evals/lm_harness_eval.py:19
Method__init__(self, hidden_size, eps=1e-5, dropout_p=0.0, device=None, dtype=None)
mamba_ssm/ops/triton/layer_norm.py:957
Method__init__(self, tile_D: int, dstate: int, mimo: int = 1, num_warps: int = 4, remove_gate: bool = False, remove_outproj:
mamba_ssm/ops/cute/mamba3/mamba3_step_fn.py:49
Method__init__(
self,
d_model,
d_state=128,
expand=2,
headdim=64,
ngroups=1,
mamba_ssm/modules/mamba3.py:27
Method__init__(self, num_embeddings, *args, process_group=None, padding_idx=None, **kwargs)
mamba_ssm/distributed/tensor_parallel.py:195
Method__init__(self, num_embeddings, embedding_dim, *args, process_group=None, **kwargs)
mamba_ssm/distributed/tensor_parallel.py:227
Function_bmm_chunk_bwd_kernel(
# Pointers to matrices
a_ptr, dout_ptr, db_ptr, res_ptr,
# Matrix dimensions
seqlen, chunk_s
mamba_ssm/ops/triton/ssd_bmm.py:111
Function_bmm_chunk_fwd_kernel(
# Pointers to matrices
a_ptr, b_ptr, out_ptr, seq_idx_ptr,
# Matrix dimensions
seqlen, chunk
mamba_ssm/ops/triton/ssd_bmm.py:37
Function_chunk_cumsum_bwd_kernel(
# Pointers to matrices
ddA_ptr, ddt_out_ptr, dt_ptr, A_ptr, dt_bias_ptr,
ddt_ptr, dA_ptr, ddt_bi
mamba_ssm/ops/triton/ssd_chunk_state.py:102
Function_chunk_cumsum_fwd_kernel(
# Pointers to matrices
dt_ptr, A_ptr, dt_bias_ptr, dt_out_ptr, dA_cumsum_ptr,
# Matrix dimension
mamba_ssm/ops/triton/ssd_chunk_state.py:40
Function_chunk_scan_bwd_dc_kernel(
# Pointers to matrices
dout_ptr, prev_states_ptr, C_ptr, dA_cumsum_ptr, seq_idx_ptr,
dc_ptr, ddA
mamba_ssm/ops/triton/ssd_chunk_scan.py:530
Function_chunk_scan_bwd_dcb_kernel(
# Pointers to matrices
x_ptr, dout_ptr, cb_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
dcb_ptr, ddA
mamba_ssm/ops/triton/ssd_chunk_scan.py:774
Function_chunk_scan_bwd_ddAcs_prev_kernel(
# Pointers to matrices
dout_ptr, prev_states_ptr, C_ptr, dA_cumsum_ptr, seq_idx_ptr,
ddA_cumsum_
mamba_ssm/ops/triton/ssd_chunk_scan.py:1198
Function_chunk_scan_bwd_ddAcs_stable_kernel(
# Pointers to matrices
x_ptr, dout_ptr, dt_ptr, dA_cumsum_ptr, cb_ptr,
ddA_cumsum_ptr,
# Mat
mamba_ssm/ops/triton/ssd_chunk_scan.py:1098
Function_chunk_scan_bwd_ddAcs_stable_kernel_old(
# Pointers to matrices
x_ptr, dout_ptr, dt_ptr, dA_cumsum_ptr, cb_ptr,
ddAcs_ptr,
# Matrix d
mamba_ssm/ops/triton/ssd_chunk_scan.py:979
Function_chunk_scan_bwd_ddAcs_unstable_kernel(
# Pointers to matrices
dout_ptr, out_ptr, dt_ptr, ddt_ptr, x_ptr, D_ptr,
ddA_cumsum_ptr, dD_ptr,
mamba_ssm/ops/triton/ssd_chunk_scan.py:889
Function_chunk_scan_bwd_dstates_kernel(
# Pointers to matrices
dout_ptr, c_ptr, dprev_states_ptr, dA_cumsum_ptr, seq_idx_ptr,
# Matrix d
mamba_ssm/ops/triton/ssd_chunk_scan.py:449
Function_chunk_scan_bwd_dx_kernel(
# Pointers to matrices
x_ptr, cb_ptr, dout_ptr, dt_ptr, dA_cumsum_ptr, D_ptr,
dx_ptr, ddt_ptr, #
mamba_ssm/ops/triton/ssd_chunk_scan.py:641
Function_chunk_scan_bwd_dz_kernel(
# Pointers to matrices
dout_ptr, out_ptr, z_ptr, x_ptr, D_ptr, outz_ptr, dz_ptr, dout_x_ptr, dD_ptr,
mamba_ssm/ops/triton/ssd_chunk_scan.py:349
Function_chunk_scan_chunk_state_bwd_dx_kernel(
# Pointers to matrices
x_ptr, cb_ptr, dout_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr, D_ptr,
b_ptr
mamba_ssm/ops/triton/ssd_combined.py:93
Function_chunk_scan_fwd_kernel(
# Pointers to matrices
cb_ptr, x_ptr, z_ptr, out_ptr, out_x_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
mamba_ssm/ops/triton/ssd_chunk_scan.py:49
Function_chunk_scan_fwd_kernel_wip(
# Pointers to matrices
cb_ptr, x_ptr, z_ptr, out_ptr, out_x_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
mamba_ssm/ops/triton/ssd_chunk_scan.py:195
Function_chunk_scan_fwd_wip(cb, x, dt, dA_cumsum, C, B, states, D=None, z=None, seq_idx=None)
mamba_ssm/ops/triton/ssd_chunk_scan.py:1311
Function_chunk_state_bwd_db_kernel(
# Pointers to matrices
x_ptr, dstates_ptr, b_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
db_ptr, dd
mamba_ssm/ops/triton/ssd_chunk_state.py:398
Function_chunk_state_bwd_ddAcs_stable_kernel(
# Pointers to matrices
x_ptr, b_ptr, dstates_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
ddA_cumsum
mamba_ssm/ops/triton/ssd_chunk_state.py:528
Function_chunk_state_bwd_dx_kernel(
# Pointers to matrices
x_ptr, b_ptr, dstates_ptr, dt_ptr, dA_cumsum_ptr,
dx_ptr, ddt_ptr, ddA_cu
mamba_ssm/ops/triton/ssd_chunk_state.py:286
Function_chunk_state_fwd_kernel(
# Pointers to matrices
x_ptr, b_ptr, states_ptr, dt_ptr, dA_cumsum_ptr, seq_idx_ptr,
# Matrix di
mamba_ssm/ops/triton/ssd_chunk_state.py:192
Function_chunk_state_varlen_kernel(
# Pointers to matrices
x_ptr, b_ptr, dt_ptr, dA_cumsum_ptr, chunk_states_ptr, cu_seqlens_ptr, states
mamba_ssm/ops/triton/ssd_chunk_state.py:640
Function_selective_scan_update_kernel(
# Pointers to matrices
state_ptr, x_ptr, dt_ptr, dt_bias_ptr, A_ptr, B_ptr, C_ptr, D_ptr, z_ptr, out
mamba_ssm/ops/triton/selective_state_update.py:24
Function_state_passing_bwd_kernel(
# Pointers to matrices
dout_ptr, out_ptr, dA_cs_ptr, dfinal_states_ptr, seq_idx_ptr,
dstates_ptr
mamba_ssm/ops/triton/ssd_state_passing.py:102
Function_state_passing_fwd_kernel(
# Pointers to matrices
states_ptr, out_ptr, final_states_ptr, dA_cs_ptr, initstates_ptr, seq_idx_ptr
mamba_ssm/ops/triton/ssd_state_passing.py:30
Function_swiglu_bwd_kernel(
X,
Y,
DOUT,
OUT,
DX,
DY,
stride_x_row, # how much to increase the pointer when
mamba_ssm/ops/triton/k_activations.py:78
Functionangle_dt_bwd_kernel(
# Outputs
GRAD_ANGLE, GRAD_DT, GRAD_INIT_STATE,
# Inputs
GRAD_OUT, GRAD_OUTPUT_STATE, ANGLE,
mamba_ssm/ops/triton/mamba3/angle_dt.py:232
Functionangle_dt_fwd_kernel(
# Outputs
OUT, OUTPUT_STATE,
# Inputs
ANGLE, DT, INIT_STATE, CU_SEQLENS,
# Strides for O
mamba_ssm/ops/triton/mamba3/angle_dt.py:24