[Router] Add load-aware prefill admission and bounded policy proposals (#37843)
Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com> Co-authored-by: Kangyan Zhou <zky314343421@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Shangming Cai <csmthu@gmail.com>
This commit is contained in:
co-authored by
Kangyan Zhou
Claude Opus 4.8
Shangming Cai
parent
d50e9a9756
commit
ecd97de1fc
@@ -64,6 +64,7 @@ fn config() -> Config {
|
||||
idle_secs: 3600,
|
||||
eviction_interval_secs: 3600,
|
||||
}),
|
||||
affinity: None,
|
||||
fused: None,
|
||||
eligibility: None,
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user