Post

Open-weight LLMs are catching up to frontier models—fast. On SWE-bench, top open models now sit within ~7 points of Claude Opus 4.7. So I built a self-hosted platform on K8s to see what it takes to run this for real today. 🧵

The stack is built for evolution: ✅ vLLM on NVIDIA L4 (fp8) ✅ Crossplane InferenceService (1 YAML = the stack) ✅ KEDA scaling on GPU batch/KV signals ✅ Envoy AI Gateway + Iris for smart semantic routing ✅ Amazon S3 Files for shared POSIX storage

0 reposts1 like