biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[PD] Change kv_load_failure_policy Default from "recompute" to "fail" (#34896)

Browse Source 
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Nicolò Lucchesi
2026-02-21 10:34:57 +01:00
committed by GitHub
parent 8dc8a99b56
commit ab6f3487a6
5 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config/kv_transfer.py
View File

@@ -61,10 +61,10 @@ class KVTransferConfig:
enable_permute_local_kv: bool = False
"""Experiment feature flag to enable HND to NHD KV Transfer"""
kv_load_failure_policy: Literal["recompute", "fail"] = "recompute"
kv_load_failure_policy: Literal["recompute", "fail"] = "fail"
"""Policy for handling KV cache load failures.
'recompute': reschedule the request to recompute failed blocks (default)
'fail': immediately fail the request with an error finish reason"""
'recompute': reschedule the request to recompute failed blocks
'fail': immediately fail the request with an error finish reason (default)"""
def compute_hash(self) -> str:
"""