DeepSpeed
2e3769a1 - Enable fused_lamb_cuda_kernel on ROCm (#2148)

Commit
2 years ago
Enable fused_lamb_cuda_kernel on ROCm (#2148) Co-authored-by: Jeff Rasley <jerasley@microsoft.com> Co-authored-by: Olatunji Ruwase <olruwase@microsoft.com> Co-authored-by: Michael Wyatt <michaelwyatt@microsoft.com>
Author
Parents
  • csrc/lamb
    • File
      fused_lamb_cuda_kernel.cu