Menü
SkillsMP hat 1 Skills aus abhiram1809/inference-god-mode gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/abhiram1809/inference-god-mode.
A skill for tuning self-hosted LLM inference around the model, hardware, API requirements, and serving workload, including parallelism, KV tiers, and prefill/decode separation.
Es werden 1 von 1 gesammelten Skills angezeigt.
Plan, 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.
Quellsprache: Englisch