pub struct NemotronSsmWeights {
pub in_proj: QuantizedWeight,
pub out_proj: QuantizedWeight,
pub conv1d_weight: DenseWeight,
pub conv1d_bias: DenseWeight,
pub a_log: DenseWeight,
pub d_param: DenseWeight,
pub dt_bias: DenseWeight,
pub ssm_norm: DenseWeight,
}Expand description
Nemotron-H Mamba-2 SSM weights.
in_proj produces [z(d_inner), x(d_inner), B(n_groupsstate), C(n_groupsstate), dt(num_heads)].
Fields§
§in_proj: QuantizedWeightin_proj: [in_proj_size, hidden_size] NVFP4.
out_proj: QuantizedWeightout_proj: [hidden_size, d_inner] NVFP4.
conv1d_weight: DenseWeightconv1d weight: [d_xBC, 1, conv_kernel] BF16.
conv1d_bias: DenseWeightconv1d bias: [d_xBC] BF16.
a_log: DenseWeightA_log: [mamba_num_heads] BF16 (cast to FP32 at runtime).
d_param: DenseWeightD skip-connection: [mamba_num_heads] BF16.
dt_bias: DenseWeightdt_bias: [mamba_num_heads] BF16.
ssm_norm: DenseWeightSSM internal norm: [d_inner] BF16 (applied to y before gating with z).
Auto Trait Implementations§
impl Freeze for NemotronSsmWeights
impl RefUnwindSafe for NemotronSsmWeights
impl Send for NemotronSsmWeights
impl Sync for NemotronSsmWeights
impl Unpin for NemotronSsmWeights
impl UnwindSafe for NemotronSsmWeights
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more