pub struct ExecutorCapabilities {
pub max_batch_size: usize,
pub max_sequence_length: usize,
pub attention_mechanisms: Vec<AttentionType>,
pub supports_dynamic_batching: bool,
pub supports_continuous_batching: bool,
pub supports_speculative_decoding: bool,
pub supports_tensor_parallelism: bool,
pub supports_pipeline_parallelism: bool,
pub supported_dtypes: Vec<DataType>,
pub supported_devices: Vec<Device>,
pub memory_requirements: MemoryRequirements,
}Expand description
Executor capabilities and configuration
Fields§
§max_batch_size: usizeMaximum supported batch size
max_sequence_length: usizeMaximum sequence length
attention_mechanisms: Vec<AttentionType>Supported attention mechanisms
supports_dynamic_batching: boolWhether executor supports dynamic batching
supports_continuous_batching: boolWhether executor supports continuous batching
supports_speculative_decoding: boolWhether executor supports speculative decoding
supports_tensor_parallelism: boolWhether executor supports tensor parallelism
supports_pipeline_parallelism: boolWhether executor supports pipeline parallelism
supported_dtypes: Vec<DataType>Supported data types
supported_devices: Vec<Device>Supported devices
memory_requirements: MemoryRequirementsMemory requirements estimation
Trait Implementations§
Source§impl Clone for ExecutorCapabilities
impl Clone for ExecutorCapabilities
Source§fn clone(&self) -> ExecutorCapabilities
fn clone(&self) -> ExecutorCapabilities
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for ExecutorCapabilities
impl Debug for ExecutorCapabilities
Source§impl<'de> Deserialize<'de> for ExecutorCapabilities
impl<'de> Deserialize<'de> for ExecutorCapabilities
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
Auto Trait Implementations§
impl Freeze for ExecutorCapabilities
impl RefUnwindSafe for ExecutorCapabilities
impl Send for ExecutorCapabilities
impl Sync for ExecutorCapabilities
impl Unpin for ExecutorCapabilities
impl UnsafeUnpin for ExecutorCapabilities
impl UnwindSafe for ExecutorCapabilities
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more