27 lines
1.1 KiB
Python
27 lines
1.1 KiB
Python
|
"""Compute per-query valid compressed entry count from block table.
|
||
|
|
|
||
|
|
Small integer reduction: for each request, valid_len = block_lens * entries_per_block
|
||
|
|
accounting for the partially-filled last block. Used by the indexer score kernel
|
||
|
|
to know how many candidate keys to stream.
|
||
|
|
"""
|
||
|
|
import torch
|
||
|
|
|
||
|
|
|
||
|
|
def compute_valid_lens(
|
||
|
|
block_lens: torch.Tensor, # [B] int32 — number of blocks per request
|
||
|
|
block_table: torch.Tensor, # [B, max_logical_blocks] int32
|
||
|
|
entries_per_block: int,
|
||
|
|
) -> torch.Tensor:
|
||
|
|
"""Return [B] int32 — total valid compressed entries per request.
|
||
|
|
|
||
|
|
For now, a simple formula: valid_entries = block_lens * entries_per_block.
|
||
|
|
This assumes all entries in all allocated blocks are valid, which is correct
|
||
|
|
because blocks are only allocated when flush writes to them, and each block
|
||
|
|
is fully populated before the next is allocated (compression ratio is fixed).
|
||
|
|
|
||
|
|
In a more general design with partially-filled blocks, this would need
|
||
|
|
to check the actual write positions. For DSV4's fixed-ratio compression,
|
||
|
|
the simple formula is exact.
|
||
|
|
"""
|
||
|
|
return block_lens * entries_per_block
|