refactor: route disagg prefill checkpoints through checkpoint_disagg_prefill shim
Upstream #42035's tests and call structure expect Scheduler.checkpoint_disagg_prefill (introduced upstream with #41520's checkpoint_kv_cache / insert_req cache API). This branch still uses maybe_cache_unfinished_req (old cache_unfinished_req API), so add a thin shim with the upstream name and route the three call sites through it. No behavior change.
This commit is contained in:
@@ -969,7 +969,7 @@ class SchedulerDisaggregationPrefillMixin:
|
||||
advance_logprob_pt(i, req)
|
||||
continue
|
||||
|
||||
maybe_cache_unfinished_req(req, self.tree_cache)
|
||||
self.checkpoint_disagg_prefill(req)
|
||||
self.disagg_prefill_inflight_queue.append(req)
|
||||
if self.spec_algorithm.is_eagle() and draft_input is not None:
|
||||
req.output_topk_p = draft_input.topk_p[i]
|
||||
@@ -1326,7 +1326,7 @@ class SchedulerDisaggregationPrefillMixin:
|
||||
chunked_req_to_exclude = set()
|
||||
if (req := self.chunked_req) is not None:
|
||||
chunked_req_to_exclude.add(req)
|
||||
maybe_cache_unfinished_req(req, self.tree_cache, chunked=True)
|
||||
self.checkpoint_disagg_prefill(req, chunked=True)
|
||||
|
||||
if not self.check_bootstrap(req):
|
||||
if is_aborted(req):
|
||||
@@ -1622,10 +1622,21 @@ class SchedulerDisaggregationPrefillMixin:
|
||||
else:
|
||||
self.disagg_prefill_pending_chunk_rids.add(req.rid)
|
||||
|
||||
def checkpoint_disagg_prefill(
|
||||
self: Scheduler, req: Req, chunked: bool = False
|
||||
) -> None:
|
||||
"""Publish the request's computed prefix to the tree cache.
|
||||
|
||||
Name shim for the #42035-era call structure: this branch predates
|
||||
#41520's ``checkpoint_kv_cache`` / ``insert_req`` cache API, so the
|
||||
equivalent here is ``maybe_cache_unfinished_req``.
|
||||
"""
|
||||
maybe_cache_unfinished_req(req, self.tree_cache, chunked=chunked)
|
||||
|
||||
def optimistic_release_and_requeue(self: Scheduler, req: Req) -> None:
|
||||
"""Release KV cache and requeue an optimistic prefill request."""
|
||||
max_attempts = get_disagg().optimistic_prefill_attempts
|
||||
maybe_cache_unfinished_req(req, self.tree_cache)
|
||||
self.checkpoint_disagg_prefill(req)
|
||||
# The cached prefix is evictable once the KV is released. Its length
|
||||
# (capped at what a retry can match) seeds the retry's storage baseline,
|
||||
# so an evicted prefix is looked up in L3 once before it is recomputed.
|
||||
|
||||
Reference in New Issue
Block a user