apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] reschedule_preempt_task append waiting & PREEMPTED blocksize (#5506)

Browse Source 
* bugfix reschedule_preempt_task append waiting & PREEMPTED blocksize

* bugfix reschedule_preempt_task append waiting & PREEMPTED blocksize

* 注释

* [bugfix] PREEMPTED task blocksize

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Daci
2025-12-12 17:43:29 +08:00
committed by GitHub
parent a389bb7c5c
commit dbedb0797b
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/engine/sched/resource_manager_v1.py
View File

@@ -261,6 +261,7 @@ class ResourceManagerV1(ResourceManager):
self.running.insert(0, preempted_req)
continue
preempted_req.status = RequestStatus.PREEMPTED
preempted_req.last_preempted_blocksize = len(preempted_req.block_tables)
preempted_req.num_computed_tokens = 0
if self.config.scheduler_config.splitwise_role == "decode":
self.tasks_list[preempted_req.idx] = None
@@ -735,6 +736,14 @@ class ResourceManagerV1(ResourceManager):
break
num_new_tokens = self._get_num_new_tokens(request, token_budget)
num_new_block = self.get_new_block_nums(request, num_new_tokens)
# If num_new_block is less than the last preempted block size, use the last preempted block size instead.
# For normal requests, when allocating blocks, we reserve two extra blocks for decoding.
# In the request rescheduling scenario, we currently only consider the number of tokens already generated,
# which might lead to allocating fewer blocks than the previous allocation, causing repeated rescheduling.
# This adjustment ensures we at least allocate as many blocks as before to avoid this issue.
last_preempted_blocksize = getattr(request, "last_preempted_blocksize", 0)
if num_new_block < last_preempted_blocksize:
num_new_block = last_preempted_blocksize
# Allocate blocks to prefill
if self.cache_manager.can_allocate_gpu_blocks(num_new_block):
if not request.get("skip_allocate", False):