For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Python function
window_row_plan
window_row_plan()
max.pipelines.speculative.gated_delta_rollback.window_row_plan(merged_offsets, num_accepted, num_draft_tokens, total_rows, device)
Plans the replay over the verify’s per-row window copy.
The verify copies each row of at most K + 1 tokens into one
K + 1 slot, so request r’s rows start at r * (K + 1) and
a row longer than the window, which the verify committed itself,
replays nothing (ring_accepted_lengths()).
-
Parameters:
-
- merged_offsets (TensorValue) –
[batch + 1]offsets of the verified sequence. - num_accepted (TensorValue) –
[batch]accepted draft tokens per request. - num_draft_tokens (TensorValue) – Scalar
Kondevice. - total_rows (Dim) – Row count of the window copy the replay gathers from.
- device (DeviceRef) – Device the plan is built on.
- merged_offsets (TensorValue) –
-
Returns:
-
which row of the window copy feeds each replay row, and the ragged offsets over them.
-
Return type:
-
(row_indices, replay_offsets)