I may be slow to respond.
Senior software architect, Ford Otosan. On-prem LLM inference, GPU clusters, coding agents.
-
Ford Otosan
- Istanbul
-
03:18
(UTC +03:00) - uzunenes.com
Highlights
- Pro
Popular repositories Loading
-
triton-server-hpa
triton-server-hpa PublicAutoscale NVIDIA Triton on Kubernetes by GPU utilisation — DCGM, Prometheus adapter, HPA, GPU time-slicing. Tested end-to-end.
-
k8s-ai-stack
k8s-ai-stack PublicProduction-ready AI for Kubernetes. Run cutting‑edge LLMs on NVIDIA GPUs with vLLM. Use Ollama for embeddings and vision. Access securely through OpenWebUI. Scalable, high‑performance, and fully se…
-
libmqttlink
libmqttlink Publiclightweight C/C++ MQTT client: background connection, auto-reconnect & re-subscribe, per-topic callbacks.
C
-
ubuntu-desktop-railway
ubuntu-desktop-railway PublicForked from bon5co/ubuntu-desktop-railway
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




