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

Open
zccjjj wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

bugfix AS block leaks #7890

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 9 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(
(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 @@ -1150,9 +1153,12 @@ 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 +1202,7 @@ def _allocate_decode_and_extend():
)
request.status = RequestStatus.RUNNING_PREFILL
else:
# Warnig: _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