wmantly 2b4e826437 Add sglang-inspired low-latency NCCL ring buffer and CUDA connection optimization flags to start-server.sh

2026-09-01 14:55:56 +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 power governor active retention during long prompt evaluations and remove redundant proxy governor thread

2026-09-01 14:40:19 +00:00

power-governor.py

Fix power governor active retention during long prompt evaluations and remove redundant proxy governor thread

2026-09-01 14:40:19 +00:00

start-server.sh

Add sglang-inspired low-latency NCCL ring buffer and CUDA connection optimization flags to start-server.sh

2026-09-01 14:55:56 +00:00

tune-gpus.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