Code

Prompt prefix caching for multi-LoRA#655

Code

Merged

tgaddair merged 8 commits intomainpredibase/lorax:mainfrom lora-prompt-cachepredibase/lorax:lora-prompt-cacheCopy head branch name to clipboardOct 23, 2024

+427-219

Commits

Commits on Oct 22, 2024

• Update OpenAPI spec

  tgaddair

  committed
  8634b04

• Update radix

  tgaddair

  committed
  1c588a2

• Plumb adapter_index

  tgaddair

  committed
  5c4fb5f

• Fixed next batch

  tgaddair

  committed
  9f0e9f7

• Docker: build

  tgaddair

  committed
  cfd249f

• Cleanup

  tgaddair

  committed
  e62b33d

Commits on Oct 23, 2024

• Debug

  tgaddair

  committed
  b37af34

• Revert docker

  tgaddair

  committed
  f6562fb