wmantly 7269a96313 fix(proxy): dynamically report exact 128K context window (131072) and Q5_K_P quantization across all API endpoints

2026-09-18 02:10:00 +00:00

..

build-nccl-llama.sh

Initial commit: Complete deployment scripts, power governor, systemd units, and architecture documentation for Turing multi-GPU LLM rig

2026-09-01 01:55:19 +00:00

ollama-proxy.py

fix(proxy): dynamically report exact 128K context window (131072) and Q5_K_P quantization across all API endpoints

2026-09-18 02:10:00 +00:00

start-server.sh

fix(memory): tune cache-ram to 12288MB to prevent host RAM OOM-kills on 48GB servers

2026-09-18 02:07:18 +00:00