Code

Fix cuda hardcode for inference woq#5565

Code

Merged

loadams merged 3 commits intodeepspeedai:masterdeepspeedai/DeepSpeed:masterfrom Liangliang-Ma:xpu_quantLiangliang-Ma/DeepSpeed:xpu_quantCopy head branch name to clipboardJun 5, 2024

+9-9

Commits

Commits on May 24, 2024

• fix cuda hardcode

  Liangliang-Ma

  committed
  90dc71b

  Copy full SHA for 90dc71b

Commits on May 27, 2024

• update rest cuda hardcode

  Liangliang-Ma

  committed
  c9c7ba5

  Copy full SHA for c9c7ba5

Commits on May 28, 2024

• Merge branch 'master' into xpu_quant

  loadams

  authored
  9c58fc9

  Copy full SHA for 9c58fc9