pub struct ChunkedPrefillPageMetadata {
pub block_table: DevicePtr,
pub seq_len: DevicePtr,
pub block_capacity: usize,
pub uploaded_blocks: usize,
}Expand description
2026-09-25: Per-sequence device copies of the paged-attention metadata for chunked prefill, kept across chunks so each chunk uploads only the block-table entries it added.
Fields§
§block_table: DevicePtr2026-09-25: The block table as 32-bit entries.
seq_len: DevicePtr2026-09-25: The running sequence length, one u32.
block_capacity: usize2026-09-25: Block-table entries allocated, sized for the whole prompt.
uploaded_blocks: usize2026-09-25: Block-table entries already uploaded.
Auto Trait Implementations§
impl Freeze for ChunkedPrefillPageMetadata
impl RefUnwindSafe for ChunkedPrefillPageMetadata
impl Send for ChunkedPrefillPageMetadata
impl Sync for ChunkedPrefillPageMetadata
impl Unpin for ChunkedPrefillPageMetadata
impl UnwindSafe for ChunkedPrefillPageMetadata
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