wmantly 1e98eea3bd chore(config): switch model to Qwen3.8-27B Q4_K_P with FastMTP 32K draft

2026-09-22 01:22:46 +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

chore(config): switch model to Qwen3.8-27B Q4_K_P with FastMTP 32K draft

2026-09-22 01:22:46 +00:00

start-server.sh

chore(config): switch model to Qwen3.8-27B Q4_K_P with FastMTP 32K draft

2026-09-22 01:22:46 +00:00