Struct BatchConfig 

pub struct BatchConfig {
    pub max_batch_size: usize,
    pub max_wait_ms: u64,
    pub enable_dynamic: bool,
    pub enable_continuous: bool,
    pub max_num_batched_tokens: usize,
}

Fields

max_batch_size: usize

max_wait_ms: u64

enable_dynamic: bool

enable_continuous: bool

max_num_batched_tokens: usize

vLLM-style per-iteration token budget. The scheduler emits a mixed prefill+decode batch summing to at most this many Q tokens (decode = 1 each, prefill chunk = its chunk size). Default 2048. Runtime snapshots can override this with FERRUM_MAX_BATCHED_TOKENS, usually from the GPU autosizer or a named workload preset rather than a user hand-written env bundle.

Trait Implementations

impl Clone for BatchConfig

fn clone(&self) -> BatchConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BatchConfig

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

Formats the value using the given formatter.

impl Default for BatchConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for BatchConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for BatchConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.