Code

GPT fast example#2815

Code

Merged

mreso merged 10 commits intomasterpytorch/serve:masterfrom feature/gpt-fastpytorch/serve:feature/gpt-fastCopy head branch name to clipboardDec 5, 2023

+509

Commits

Commits on Dec 1, 2023

• Initial commit for gpt_fast example

  Show description for f7eb055
  mreso

  committed
  f7eb055

  Copy full SHA for f7eb055

• Add int8 quantization to example

  mreso

  committed
  f158d29

  Copy full SHA for f158d29

Commits on Dec 2, 2023

• Add missing json file

  mreso

  committed
  c3fffcf

  Copy full SHA for c3fffcf

• Enable streaming response

  mreso

  committed
  0f0ea6b

  Copy full SHA for 0f0ea6b

• Remove print

  mreso

  committed
  8f35092

  Copy full SHA for 8f35092

• Adapt unit test to list return value, fix lint error

  mreso

  committed
  ccbd4e8

  Copy full SHA for ccbd4e8

• Merge branch 'master' into feature/gpt-fast

  agunapal

  authored
  10910a8

  Copy full SHA for 10910a8

Commits on Dec 4, 2023

• Assert if batch_size is not 1

  mreso

  committed
  e640b39

  Copy full SHA for e640b39

• Addressed review comments

  mreso

  committed
  aefb14b

  Copy full SHA for aefb14b

Commits on Dec 5, 2023

• Added GPU compatibility remark

  mreso

  committed
  8394d53

  Copy full SHA for 8394d53