sirius0xdev 7e7b7d414d fix: restrict KEDA scaling to /v1/(chat/)?completions paths only ... - Switch to HTTPScaledObject (matches a100 pattern) - Probes (/health, /v1/models) now ignored for scaling - Keeps fast polling (10s), quick cooldown (30s), 15min idle scale-to-0 Health/readiness/startup probes hit pod IP directly (bypass service), so never triggered scaling anyway — but paths ensure only inference traffic scales.		2026-04-29 04:14:46 +00:00
..
keda-gpu-scaling	fix: restrict KEDA scaling to /v1/(chat/)?completions paths only	2026-04-29 04:14:46 +00:00
vllm-servers	feat: optimize RTX6000 vLLM KEDA scaling	2026-04-29 04:12:36 +00:00