sarman/tftsr_ai: ai-platform -- Local AI Server Automation Ansible automation for full lifecycle management of a server as a local AI inference platform. This project provisions, configures, benchmarks, and maintains every service required to run Ollama-based LLM inference behind NGINX reverse proxy with SSO, vector search (RAG), DNS, secret management, and Telegram bot access -- all driven by a single ansible-playbook deploy_ai.yml command.

Shaun Arman d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics		1 день назад
..
.gitkeep	c9457bb38b Initial release: full-stack local AI platform automation	6 дней назад
benchmark_20260307T125148.md	c9457bb38b Initial release: full-stack local AI platform automation	6 дней назад
benchmark_20260307T161036.md	9472c9dbe4 Fix warmup service bugs and add CLAUDE.md	6 дней назад
benchmark_20260307T161220.md	9472c9dbe4 Fix warmup service bugs and add CLAUDE.md	6 дней назад
benchmark_20260307T161721.md	9472c9dbe4 Fix warmup service bugs and add CLAUDE.md	6 дней назад
benchmark_20260307T163017.md	9472c9dbe4 Fix warmup service bugs and add CLAUDE.md	6 дней назад
benchmark_20260307T170059.md	55d412f85d Add three-pass benchmark with size-aware tier routing	5 дней назад
benchmark_20260307T174357.md	fb7c5f1061 Tune Ollama performance: fix HT regression, add OS tuning, KV cache quant	5 дней назад
benchmark_20260307T175402.md	fb7c5f1061 Tune Ollama performance: fix HT regression, add OS tuning, KV cache quant	5 дней назад
benchmark_20260307T184212.md	55d412f85d Add three-pass benchmark with size-aware tier routing	5 дней назад
benchmark_20260308T003605.md	55d412f85d Add three-pass benchmark with size-aware tier routing	5 дней назад
benchmark_20260308T145246.md	08203de7f5 Enhance benchmark pipeline with improved async handling and error detection	4 дней назад
benchmark_20260308T215747.md	08203de7f5 Enhance benchmark pipeline with improved async handling and error detection	4 дней назад
benchmark_20260309T080551.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260309T174604.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T094843.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T102149.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T110632.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T122818.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T160815.md	d9450d0c08 fix(benchmark): refine model selection and enhance evaluation metrics	1 день назад
benchmark_20260310T170013.md	3b9e8951df fix(benchmark): prevent deepseek:latest re-pull; Run 7 achieves target Node 0 layout	1 день назад
benchmark_review_20260310.md	3b9e8951df fix(benchmark): prevent deepseek:latest re-pull; Run 7 achieves target Node 0 layout	1 день назад
model_selection.json	3b9e8951df fix(benchmark): prevent deepseek:latest re-pull; Run 7 achieves target Node 0 layout	1 день назад