Nybble™
SnackStackHack
LLMOps: Serving and Operating LLMs

Course wrap-up

Lessons

  1. 1. The model serving stack
  2. 2. vLLM and production model servers
  3. 3. Inference optimization
  4. 4. Model compression: PTQ, QAT, and calibration
  5. 5. Pruning and distillation
  6. 6. Streaming and real-time delivery
  7. 7. Building LLM APIs
  8. 8. Model routing and fallbacks
  9. 9. Caching strategies
  10. 10. Input guardrails
  11. 11. Output guardrails
  12. 12. The OWASP Top 10 for LLM applications
  13. 13. LLM observability
  14. 14. Cost control
  15. 15. Capacity planning and scaling
  16. 16. Incident response and runbooks
  17. 17. Capstone — a production LLM service
  18. Key takeaways
  19. How to get certified
  20. Your certificate

Your certificate

Certificates are issued to an account — it's what ties the credential to a name a reader can check. Sign in to see where you stand on LLMOps: Serving and Operating LLMs.

← PreviousBack to course

Nybble™ — built for the people building AI.

AboutTermsPrivacyContact
SnackStackHack
Message Nybble