Code

Adding fp8 to gradlib#44

Code

Merged

charlifu merged 15 commits intomainROCm/vllm:mainfrom charlifu/adding_fp8_gradlibROCm/vllm:charlifu/adding_fp8_gradlibCopy head branch name to clipboardJun 10, 2024

+731-404

Commits

Commits on Jun 6, 2024

• adding fp8 gemm tunner to gradlib

  charlifu

  committed
  7e46e13

  Copy full SHA for 7e46e13

• formatting

  charlifu

  committed
  7161b1c

  Copy full SHA for 7161b1c

Commits on Jun 7, 2024

• Merge branch 'main' into charlifu/adding_fp8_gradlib

  charlifu

  committed
  0a9e750

  Copy full SHA for 0a9e750

• add instructions

  charlifu

  committed
  11726d3

  Copy full SHA for 11726d3

• Linting

  mawong-amd

  committed
  12d3b25

  Copy full SHA for 12d3b25

• adding fp8 gemm tunner to gradlib

  Show description for e96b25e
  

  charlifu

  authored and

  mawong-amd

  committed
  e96b25e

  Copy full SHA for e96b25e

• Linting fp8 gradlib

  mawong-amd

  committed
  03e97c2

  Copy full SHA for 03e97c2

• Merge branch 'charlifu/adding_fp8_gradlib' of https://github.com/ROCm/vllm into charlifu/adding_fp8_gradlib

  charlifu

  committed
  92faa59

  Copy full SHA for 92faa59

• fix merging issue of ROCm_performance.md

  charlifu

  committed
  a186903

  Copy full SHA for a186903

• delete fp8_gemm_tuner.py

  charlifu

  committed
  1778136

  Copy full SHA for 1778136

• Fix linting for triton: unmeld if with constexpr

  mawong-amd

  committed
  c6c3d30

  Copy full SHA for c6c3d30

• update tutorial

  charlifu

  committed
  bb8e509

  Copy full SHA for bb8e509

• Merge branch 'main' of github.com:ROCm/vllm into charlifu/adding_fp8_gradlib

  mawong-amd

  committed
  4d7f7c0

  Copy full SHA for 4d7f7c0

• Fix linting again

  mawong-amd

  committed
  e6a0c53

  Copy full SHA for e6a0c53

Commits on Jun 10, 2024

• fix typo

  charlifu

  committed
  e4aa7d4

  Copy full SHA for e4aa7d4