TargetLevers

spark_model::layers::ops::target_defaults

Struct TargetLevers 

Source 
pub struct TargetLevers {
Show 15 fields
    pub hw: &'static str,
    pub lm_head_batchm_max: Resolved<u32>,
    pub ssm_batched_recurrent: Resolved<bool>,
    pub gdn_prefill_tc: Resolved<bool>,
    pub ssm_ba_gates_hopper: Resolved<bool>,
    pub fp8_act_quant_hopper: Resolved<bool>,
    pub decode_split_silu: Resolved<bool>,
    pub attn_decode_splitk: Resolved<SplitkPolicy>,
    pub ffn_m16_tc: Resolved<bool>,
    pub attn_m16_tc: Resolved<bool>,
    pub lm_head_m16_tc: Resolved<bool>,
    pub attn_ncol_gemv: Resolved<bool>,
    pub ffn_gateup_fused: Resolved<bool>,
    pub w8a8_prefill_max_m_widening: Resolved<u32>,
    pub w8a8_prefill_max_m_narrowing: Resolved<u32>,

}
Expand description

Every serving lever this target declares, resolved against the environment.

Field order is the order the serve log prints them in.

Fields§

§hw: &'static str

kernels/<hw> this binary was compiled from, for the log line only.

§lm_head_batchm_max: Resolved<u32>§ssm_batched_recurrent: Resolved<bool>§gdn_prefill_tc: Resolved<bool>§ssm_ba_gates_hopper: Resolved<bool>§fp8_act_quant_hopper: Resolved<bool>§decode_split_silu: Resolved<bool>§attn_decode_splitk: Resolved<SplitkPolicy>§ffn_m16_tc: Resolved<bool>

The w8a16_gemm_m16 tier on the dense-FFN decode arm (#927).

§attn_m16_tc: Resolved<bool>

The w8a16_gemm_m16 tiers on the decode Q/K/V and o_proj (#927).

§lm_head_m16_tc: Resolved<bool>

The dense_gemm_m16_bf16 arm on the BF16 decode head (#927).

§attn_ncol_gemv: Resolved<bool>

w8a16_gemv_batch16_ncol{2,4} on the decode attention projections (#927). No serving receipt on any target — off everywhere.

§ffn_gateup_fused: Resolved<bool>§w8a8_prefill_max_m_widening: Resolved<u32>§w8a8_prefill_max_m_narrowing: Resolved<u32>

Trait Implementations§

Source§

impl Clone for TargetLevers

Source§

fn clone(&self) -> TargetLevers

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 Debug for TargetLevers

Source§

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more
Source§

impl PartialEq for TargetLevers

Source§

fn eq(&self, other: &TargetLevers) -> bool

Tests for self and other values to be equal, and is used by ==.
1.0.0 · Source§

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.
Source§

impl Copy for TargetLevers

Source§

impl Eq for TargetLevers

Source§

impl StructuralPartialEq for TargetLevers

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
§

impl<Q, K> Equivalent<K> for Q
where Q: Eq + ?Sized, K: Borrow<Q> + ?Sized,

§

fn equivalent(&self, key: &K) -> bool

Compare self to key and return true if they are equal.
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