Files
homelab/k8s
Story Crater Bot d42ee34bd5 reasoning: halve max-num-seqs to 2 for Kimi swap's first boot
New model's weight footprint (35B total MoE at on-the-fly bnb-4bit) leaves
less confirmed KV-cache headroom on the 32GB card than the old one had --
reducing concurrent-sequence worst case until real memory use is verified.
2026-08-19 18:14:22 -07:00
..