#001inference-god-mode1 skills00mis à jour 2 oct. 2026100 % du créateurskillmétierdescriptionmis à jourinference-optimizernon classéPlan, deploy, benchmark, and tune self-hosted open-weight LLM inference on one machine or Kubernetes GPU clusters, including quantization, full-context capacity, OpenAI or Anthropic APIs, cache-aware routing, and prefill/decode disaggregation.2 oct. 2026Affichage de 1 skills collectés sur 1.Charger 0 skills de plusChargement des skills...