LoraKernels

Struct LoraKernels 

Source
pub struct LoraKernels {
    pub gemv_k: KernelHandle,
    pub gemm_tc_k: KernelHandle,
    pub gemm_tc_acc_k: KernelHandle,
    pub gemm_k: KernelHandle,
    pub scaled_add_k: KernelHandle,
    pub bgmv_shrink_k: KernelHandle,
    pub bgmv_expand_fold_k: KernelHandle,
    pub moe_down_shrink_k: KernelHandle,
    pub moe_down_expand_fold_k: KernelHandle,
    pub moe_gather_shrink_k: KernelHandle,
    pub moe_gather_expand_fold_k: KernelHandle,
}
Expand description

Resolved once at adapter load (module names per common/KERNEL.toml: gemv=dense_gemv_bf16.cu, gemm_tc=dense_gemm_tc.cu, gemm=dense_gemm_bf16.cu, residual_add=residual_add.cu — stem, no override).

Fields§

§gemv_k: KernelHandle§gemm_tc_k: KernelHandle§gemm_tc_acc_k: KernelHandle

Fused expand+fold (C += scale * A@B^T). 0 on miss -> the unfused gemm_tc + scaled_add pair, which is what this replaces.

§gemm_k: KernelHandle§scaled_add_k: KernelHandle§bgmv_shrink_k: KernelHandle

M2 fused batched bgmv (per-request routing): shrink then expand+fold. Module “lora_bgmv” (stem == module — no KERNEL.toml override).

§bgmv_expand_fold_k: KernelHandle§moe_down_shrink_k: KernelHandle

Feature-1 device-side MoE expert down_proj fold: shrink then expand+fold, keyed on expert via device expert_offsets. Module “moe_lora_grouped_down” (stem == module). KernelHandle(0) on miss (e.g. non-CUDA builds) — the launcher bails loudly rather than dispatching a null handle.

§moe_down_expand_fold_k: KernelHandle§moe_gather_shrink_k: KernelHandle

SOLID Incr-4 DECODE-path MoE expert down_proj fold: shrink then expand+fold, keyed on expert via the per-slot indices array (the unsorted slot-major analogue of moe_down_*_k). Module “moe_lora_gather_bgmv” (stem == module). KernelHandle(0) on miss (e.g. non-CUDA builds) — the launcher bails loudly rather than dispatching null.

§moe_gather_expand_fold_k: KernelHandle

Implementations§

Source§

impl LoraKernels

Source

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

Trait Implementations§

Source§

impl Clone for LoraKernels

Source§

fn clone(&self) -> LoraKernels

Returns a duplicate of the value. Read more
1.0.0 · Source§

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source. Read more
Source§

impl Copy for LoraKernels

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> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. 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> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
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