Code

[LLM Inference] Support qwen2#8893

Code

Merged

wawltor merged 9 commits intoPaddlePaddle:developPaddlePaddle/PaddleNLP:developfrom yuanlehome:support_qwen2yuanlehome/PaddleNLP:support_qwen2Copy head branch name to clipboardAug 12, 2024

+1,008-3

Commits

Commits on Aug 6, 2024

• stage 1

  yuanlehome

  committed
  e410e4a

• update

  yuanlehome

  committed
  6f9d819

Commits on Aug 7, 2024

• update

  yuanlehome

  committed
  244802a

• Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleNLP into support_llama3

  yuanlehome

  committed
  bc75f59

• support qwen2 bf16/wint8

  yuanlehome

  committed
  a6bde28

Commits on Aug 8, 2024

• add qwen2 ptq map

  yuanlehome

  committed
  1b063ac

Commits on Aug 12, 2024

• Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleNLP into support_qwen2

  yuanlehome

  committed
  febe651

• update

  yuanlehome

  committed
  6091ccb

• fix tune_cublaslt_gemm.cu

  yuanlehome

  committed
  cc76b25