[Core][Refactor] Move KV cache planning logic to kv_cache_planning.py (#61183)

Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dakai An
2026-10-13 03:05:39 +00:00
committed by GitHub
co-authored by Yifan Qiao Claude Opus 5.5
parent c077dc663d
commit df6c7ad031
21 changed files with 4043 additions and 3935 deletions
+1 -1
View File
@@ -6206,7 +6206,7 @@ class GPUModelRunner(
gc.collect()
def _init_minimal_kv_cache_for_profiling(self) -> None:
from vllm.v1.core.kv_cache_utils import (
from vllm.v1.core.kv_cache_planning import (
get_kv_cache_config_from_groups,
get_kv_cache_groups,
)