xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 05:25:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix a config typo in disable_hybrid_kv_cache_manager configuration (#19383)

Browse Source 
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
This commit is contained in:
Siyuan Liu 2025-06-09 16:41:51 -07:00 committed by GitHub
parent 8058c91108
commit 3a7cd627a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config.py
View File

@ -4497,13 +4497,13 @@ class VllmConfig:
# warning message here and will log it later.
if not (current_platform.is_cuda() or current_platform.is_rocm()):
# Hybrid KV cache manager is not supported on non-GPU platforms.
self.disable_hybrid_kv_cache_manager = True
self.scheduler_config.disable_hybrid_kv_cache_manager = True
if self.kv_transfer_config is not None:
# Hybrid KV cache manager is not compatible with KV transfer.
self.disable_hybrid_kv_cache_manager = True
self.scheduler_config.disable_hybrid_kv_cache_manager = True
if self.kv_events_config is not None:
# Hybrid KV cache manager is not compatible with KV events.
self.disable_hybrid_kv_cache_manager = True
self.scheduler_config.disable_hybrid_kv_cache_manager = True
def update_sizes_for_sequence_parallelism(self,
possible_sizes: list) -> list: