Add SGLang deployment section

#1

Move SGLang to a top-level deployment section, mirroring the vLLM block:

  • Reorder the Inference bullet list to put SGLang under vLLM
  • Update the bullet's link to the new in-page section anchor
  • Add an ## SGLang section with installation (docker tags + install guide), a basic launch command, and an EAGLE speculative-decoding launch variant
  • Link to the SGLang cookbook entry for the full deployment guide and benchmarks
juliendenize changed pull request status to merged
Mistral AI_ org

Thanks !

Sign up or log in to comment