SharedMemoryPool

Struct SharedMemoryPool 

Source
pub struct SharedMemoryPool { /* private fields */ }
Expand description

Shared memory pool for multiple models.

Manages multiple virtual memory pools with a global physical memory limit. Enables memory sharing across models with per-model statistics.

§Example

use candle_cuda_vmm::SharedMemoryPool;
use candle_core::Device;

let device = Device::new_cuda(0)?;
let mut shared_pool = SharedMemoryPool::new(
    32 * 1024 * 1024 * 1024, // 32GB global physical limit
    device,
)?;

// Register models
shared_pool.register_model("llama-7b", 64 * 1024 * 1024 * 1024)?; // 64GB virtual
shared_pool.register_model("gpt2", 32 * 1024 * 1024 * 1024)?;     // 32GB virtual

// Allocate for specific model
let addr = shared_pool.allocate_for_model("llama-7b", 1024 * 1024 * 1024)?;

Implementations§

Source§

impl SharedMemoryPool

Source

pub fn new(physical_limit: usize, device: Device) -> Result<Self>

Create shared pool with global physical memory limit.

§Arguments
  • physical_limit - Global physical memory limit (bytes).
  • device - CUDA device.
§Returns

Shared memory pool.

Source

pub fn register_model( &mut self, model_id: &str, virtual_capacity: usize, ) -> Result<()>

Register a model with virtual address space reservation.

§Arguments
  • model_id - Unique model identifier.
  • virtual_capacity - Virtual address space for this model (bytes).
§Errors

Returns error if model already registered.

Source

pub fn allocate_for_model( &mut self, model_id: &str, size: usize, ) -> Result<usize>

Allocate from specific model’s pool.

§Arguments
  • model_id - Model identifier.
  • size - Size to allocate (bytes).
§Returns

Virtual address of allocated region.

§Errors

Returns error if:

  • Model not found
  • Global physical limit exceeded
  • Allocation fails
Source

pub fn deallocate_for_model( &mut self, model_id: &str, offset: usize, size: usize, ) -> Result<()>

Free from specific model’s pool.

§Arguments
  • model_id - Model identifier.
  • offset - Offset in model’s virtual address space (bytes).
  • size - Size to free (bytes).
Source

pub fn get_model_stats(&self, model_id: &str) -> Option<MemoryStats>

Get per-model memory statistics.

Source

pub fn global_stats(&self) -> GlobalMemoryStats

Global memory statistics.

Source

pub fn unregister_model(&mut self, model_id: &str) -> Result<()>

Unregister a model and free its resources.

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.

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> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
Source§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
Source§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. 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.
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
Source§

impl<T> ErasedDestructor for T
where T: 'static,