Skip to content

[Bugfix] AS block leaks #7890

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kevincheng2 merged 2 commits into from
May 25, 2026
+10 −2
Merged

[Bugfix] AS block leaks #7890

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8d760e5
[bugfix] AS block leaks
zccjjj May 22, 2026
7b4af55
Merge branch 'develop' into ASBlockLeaks
plusNew001 May 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions fastdeploy/engine/sched/resource_manager_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1070,9 +1070,12 @@ def _allocate_decode_and_extend():
self.cache_manager.num_cpu_blocks > 0
or self.config.cache_config.kvcache_storage_backend
):
if not self.cache_manager.can_allocate_gpu_blocks(
can_schedule_block_num_threshold = self._get_can_schedule_prefill_threshold_block(

@PaddlePaddle-bot PaddlePaddle-bot May 25, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🟡 建议 此修复路径缺少对应的单元测试。

建议在 tests/scheduler/ 下补充测试用例，覆盖 enable_prefix_caching=True + num_cpu_blocks > 0（或 kvcache_storage_backend 非空）场景下，_get_can_schedule_prefill_threshold_block 阈值计算是否正确阻止了 block 泄漏。

(request.need_prefill_tokens + self.config.cache_config.block_size - 1)
// self.config.cache_config.block_size
)
if not self.cache_manager.can_allocate_gpu_blocks(
can_schedule_block_num_threshold
): # to prevent block allocation for matching in hierarchical cache and cause dead lock
break
success = self.get_prefix_cached_blocks(request)
Expand Down Expand Up @@ -1134,6 +1137,7 @@ def _allocate_decode_and_extend():
self.req_dict[request.request_id] = allocated_position
llm_logger.debug(f"req_id:{request.request_id} allocate pos end")
else:
# Warning: _free_blocks before update_cache_blocks may cause storage blocks leak
if self.config.cache_config.enable_prefix_caching:
self._free_blocks(request)
break
Expand All @@ -1150,9 +1154,12 @@ def _allocate_decode_and_extend():
self.cache_manager.num_cpu_blocks > 0
or self.config.cache_config.kvcache_storage_backend
):
if not self.cache_manager.can_allocate_gpu_blocks(
can_schedule_block_num_threshold = self._get_can_schedule_prefill_threshold_block(
(request.need_prefill_tokens + self.config.cache_config.block_size - 1)
// self.config.cache_config.block_size
)
if not self.cache_manager.can_allocate_gpu_blocks(
can_schedule_block_num_threshold
): # to prevent block allocation for matching in hierarchical cache and cause dead lock
break
success = self.get_prefix_cached_blocks(request)
Expand Down Expand Up @@ -1196,6 +1203,7 @@ def _allocate_decode_and_extend():
)
request.status = RequestStatus.RUNNING_PREFILL
else:
# Warning: _free_blocks before update_cache_blocks may cause storage blocks leak
if self.config.cache_config.enable_prefix_caching:
self._free_blocks(request)
break
Expand Down
Loading