Qwen35Kernels

metrale_model_layers::forward::qwen3_5

Struct Qwen35Kernels 

Source 
pub struct Qwen35Kernels {
Show 27 fields
    pub rms: KernelHandle,
    pub rope: KernelHandle,
    pub kvap: KernelHandle,
    pub attn: KernelHandle,
    pub sg: KernelHandle,
    pub add_rms: KernelHandle,
    pub qkv_split: KernelHandle,
    pub conv1d: KernelHandle,
    pub gdn_gate: KernelHandle,
    pub sigmoid: KernelHandle,
    pub gdn_dec: KernelHandle,
    pub kvap_turbo8: KernelHandle,
    pub attn_turbo8: KernelHandle,
    pub kvap_turbo4: KernelHandle,
    pub attn_turbo4: KernelHandle,
    pub kvap_turbo3: KernelHandle,
    pub attn_turbo3: KernelHandle,
    pub kvap_turbo2: KernelHandle,
    pub attn_turbo2: KernelHandle,
    pub kvap_bf16k_turbo4v: KernelHandle,
    pub attn_bf16k_turbo4v: KernelHandle,
    pub kvap_bf16k_turbo3v: KernelHandle,
    pub attn_bf16k_turbo3v: KernelHandle,
    pub kvap_bf16k_turbo2v: KernelHandle,
    pub attn_bf16k_turbo2v: KernelHandle,
    pub wht: KernelHandle,
    pub wht_inv: KernelHandle,

}
Expand description

2026-09-25: Kernel handles for both layer forwards, looked up once by Self::resolve.

Fields§

§rms: KernelHandle§rope: KernelHandle§kvap: KernelHandle§attn: KernelHandle§sg: KernelHandle§add_rms: KernelHandle§qkv_split: KernelHandle§conv1d: KernelHandle§gdn_gate: KernelHandle§sigmoid: KernelHandle§gdn_dec: KernelHandle§kvap_turbo8: KernelHandle

2026-09-25: Turbo KV cache kernels: quantizing appends, dequantizing decode attentions, and the WHT rotations around them. resolve looks them up even for a bf16 cache, so a missing one fails at startup.

§attn_turbo8: KernelHandle§kvap_turbo4: KernelHandle§attn_turbo4: KernelHandle§kvap_turbo3: KernelHandle§attn_turbo3: KernelHandle§kvap_turbo2: KernelHandle§attn_turbo2: KernelHandle§kvap_bf16k_turbo4v: KernelHandle§attn_bf16k_turbo4v: KernelHandle§kvap_bf16k_turbo3v: KernelHandle§attn_bf16k_turbo3v: KernelHandle§kvap_bf16k_turbo2v: KernelHandle§attn_bf16k_turbo2v: KernelHandle§wht: KernelHandle§wht_inv: KernelHandle

Implementations§

Source§

impl Qwen35Kernels

Source

pub fn resolve(gpu: &dyn GpuBackend) -> Result<Self>

2026-09-25: Looks up every kernel both layer forwards use; returns an error if any is missing.

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> Instrument for T

§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more
§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

§

fn vzip(self) -> V

§

impl<T> WithSubscriber for T

§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,