[BugFix] Fix async scheduling + chunked prefill + preemption (#28787)
Signed-off-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
@@ -778,9 +778,7 @@ class Scheduler(SchedulerInterface):
|
||||
assert not scheduled_in_prev_step
|
||||
resumed_req_ids.add(req_id)
|
||||
if not scheduled_in_prev_step:
|
||||
all_token_ids[req_id] = req.all_token_ids[
|
||||
: req.num_computed_tokens + num_tokens
|
||||
]
|
||||
all_token_ids[req_id] = req.all_token_ids.copy()
|
||||
new_block_ids.append(
|
||||
req_to_new_blocks[req_id].get_block_ids(allow_none=True)
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user