xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-29 04:00:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Honor enable_caching in connector-delayed kvcache load case (#19435)

Browse Source 
Signed-off-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Nick Hill 2025-06-13 02:46:32 -07:00 committed by GitHub
parent d70bc7c029
commit 7e8d97dd3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/v1/core/kv_cache_manager.py
View File

@ -381,10 +381,11 @@ class KVCacheManager:
self.coordinator.get_blocks(request_id)).get_block_ids()
def cache_blocks(self, request: Request, num_computed_tokens: int) -> None:
"""Cache the blocks for the request."""
block_hashes = self.req_to_block_hashes[request.request_id]
self.coordinator.cache_blocks(request, block_hashes,
num_computed_tokens)
"""Cache the blocks for the request, if enabled."""
if self.enable_caching:
block_hashes = self.req_to_block_hashes[request.request_id]
self.coordinator.cache_blocks(request, block_hashes,
num_computed_tokens)
def create_empty_block_list(self) -> KVCacheBlocks:
"""Creates a new KVCacheBlocks instance with no blocks."""

1
vllm/v1/core/sched/scheduler.py
View File

@ -1015,6 +1015,7 @@ class Scheduler(SchedulerInterface):
num_computed_tokens = min(num_computed_tokens, request.num_tokens)
if num_computed_tokens == request.num_tokens:
num_computed_tokens -= 1
# This will cache the blocks iff caching is enabled.
self.kv_cache_manager.cache_blocks(request, num_computed_tokens)
# Update the request state for scheduling.