[router] Tokenize prompt once at ingress; forward input_ids to the engine (all policies) (#28744)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
c3bae61e16
commit
364bf976be
@@ -10,11 +10,14 @@
|
||||
|
||||
mod common;
|
||||
|
||||
mod cache_aware_input_ids;
|
||||
mod chat_routing;
|
||||
mod failover;
|
||||
mod graceful_shutdown;
|
||||
mod header_forwarding;
|
||||
mod pd_bootstrap_injection;
|
||||
mod pd_pool_isolation;
|
||||
mod roundrobin_input_ids;
|
||||
mod sticky_input_ids;
|
||||
mod sticky_routing;
|
||||
mod timeout;
|
||||
|
||||
Reference in New Issue
Block a user