wmantly 261631457c Update start-server.sh with validated ngram context-lookup speculation and NCCL pipeline flags

2026-09-01 15:56:43 +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

Update start-server.sh with validated ngram context-lookup speculation and NCCL pipeline flags

2026-09-01 15:56:43 +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