wmantly cd989b3e70 feat: update to Q5_K_P @ 128K ctx, non-blocking proxy sessions, and full multi-GPU benchmark suite

2026-09-13 02:14:25 +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

feat: update to Q5_K_P @ 128K ctx, non-blocking proxy sessions, and full multi-GPU benchmark suite

2026-09-13 02:14:25 +00:00

start-server.sh

feat: update to Q5_K_P @ 128K ctx, non-blocking proxy sessions, and full multi-GPU benchmark suite

2026-09-13 02:14:25 +00:00