Skip to main content

KvCacheQuant

Struct KvCacheQuant 

Source
pub struct KvCacheQuant<B: BackendKvDtype<K>, K: KvDtypeKind> {
Show 13 fields pub k: <B as BackendKvDtype<K>>::KvBuffer, pub v: <B as BackendKvDtype<K>>::KvBuffer, pub k_scales: <B as BackendKvDtype<K>>::KvScales, pub v_scales: <B as BackendKvDtype<K>>::KvScales, pub len: usize, pub capacity: usize, pub num_kv_heads: usize, pub head_dim: usize, pub block_size: usize, pub block_table: Option<B::Buffer>, pub context_lens: Option<B::Buffer>, pub paged_block_indices: Vec<u32>, pub _kv_dtype: PhantomData<K>,
}
Expand description

Quantized-KV cache (Dim 5 INT8 / future FP8 paths). Sibling of KvCache for backends that store K/V in a non-FP16 element type plus per-token per-kv-head scales.

Why a separate struct: the FP16 KvCache<B, K> uses B::Buffer uniformly, which is FP16 on every concrete backend. Stuffing INT8 storage into that buffer would require unsafe transmutes; making the FP16 struct generic over the storage type would force every existing call site (4 model files, ~20 functions) to pick up an equality-bound on the associated type. Keeping a parallel struct for INT8 is the cheaper trade — the kernel launchers in [crate::int8_kv] take cudarc primitives directly anyway.

KStorage and ScaleStorage come from BackendKvDtype<K>::KvBuffer and BackendKvDtype<K>::KvScales. On CUDA they wrap CudaSlice<i8> and CudaSlice<f16>.

Fields§

§k: <B as BackendKvDtype<K>>::KvBuffer§v: <B as BackendKvDtype<K>>::KvBuffer§k_scales: <B as BackendKvDtype<K>>::KvScales§v_scales: <B as BackendKvDtype<K>>::KvScales§len: usize§capacity: usize§num_kv_heads: usize§head_dim: usize§block_size: usize§block_table: Option<B::Buffer>§context_lens: Option<B::Buffer>§paged_block_indices: Vec<u32>§_kv_dtype: PhantomData<K>

Auto Trait Implementations§

§

impl<B, K> Freeze for KvCacheQuant<B, K>
where <B as BackendKvDtype<K>>::KvBuffer: Freeze, <B as BackendKvDtype<K>>::KvScales: Freeze, <B as Backend>::Buffer: Freeze,

§

impl<B, K> RefUnwindSafe for KvCacheQuant<B, K>

§

impl<B, K> Send for KvCacheQuant<B, K>

§

impl<B, K> Sync for KvCacheQuant<B, K>

§

impl<B, K> Unpin for KvCacheQuant<B, K>
where <B as BackendKvDtype<K>>::KvBuffer: Unpin, <B as BackendKvDtype<K>>::KvScales: Unpin, <B as Backend>::Buffer: Unpin, K: Unpin,

§

impl<B, K> UnsafeUnpin for KvCacheQuant<B, K>

§

impl<B, K> UnwindSafe for KvCacheQuant<B, K>

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.

Source§

impl<T> Instrument for T

Source§

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

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

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.
Source§

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

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

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
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

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