Skip to content

Commit cd5866b

Browse files
toslali-ibmclaude
andcommitted
Update inference-sim submodule to latest version
- Update to commit c7529ff (adds ServeGen workload generator PR10) - Includes: startup policy logging, workload spec support, native ServeGen loading - Also update routing_policy.yaml (user-modified weights: cache=0.1, load=0.9) New features in inference-sim: - ServeGen-informed workload generator (PR10) - Multi-client workload specs with realistic distributions - Gamma/Weibull arrivals, Pareto-LogNormal inputs - Native ServeGen data loading from chunk files - Trace v2 format replay Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1 parent cc491b2 commit cd5866b

2 files changed

Lines changed: 3 additions & 3 deletions

File tree

examples/blis_router/routing_policy.yaml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@ admission:
33

44
routing:
55
policy: weighted
6-
cache_weight: 0.6
7-
load_weight: 0.4
6+
cache_weight: 0.1
7+
load_weight: 0.9
88

99
priority:
1010
policy: constant

0 commit comments

Comments
 (0)