Support streaming session on NPU (#32597)

This commit is contained in:
ming_wang
2026-08-24 14:07:44 +08:00
committed by GitHub
parent 852b04b358
commit 97b176e64c
2 changed files with 24 additions and 1 deletions
@@ -101,6 +101,8 @@ _OWNER_SITES = {
(_SS, "StreamingSession.try_cache_finished_req", "kv_allocated_len"): 1,
# Inherit the authoritative finished length (not the lagging req clock).
(_SS, "StreamingSession.try_cache_finished_req", "kv_committed_len"): 1,
# NPU page-boundary clamp on req and slot clocks.
(_SS, "StreamingSession.try_match_prefix", "kv_committed_len"): 2,
}