Skip to content

feat(core): add support for BLAS and optimize linear operations#375

Merged
chenghuaWang merged 1 commit intoUbiquitousLearning:v2from
chenghuaWang:v2
Aug 15, 2025
Merged

feat(core): add support for BLAS and optimize linear operations#375
chenghuaWang merged 1 commit intoUbiquitousLearning:v2from
chenghuaWang:v2

Conversation

@chenghuaWang
Copy link
Copy Markdown
Collaborator

  • Add BLAS support for matrix operations
  • Optimize LinearOp and MatMulOp using BLAS
  • Implement Conv3DOp for ARM architectures
  • Update MultimodalRoPEOp to use precomputed embeddings
  • Refactor EmbeddingOp, LayerNormOp, and RMSNormOp for better parameter handling
  • Add guide for adding new data types

- Add BLAS support for matrix operations
- Optimize LinearOp and MatMulOp using BLAS
- Implement Conv3DOp for ARM architectures
- Update MultimodalRoPEOp to use precomputed embeddings
- Refactor EmbeddingOp, LayerNormOp, and RMSNormOp for better parameter handling
- Add guide for adding new data types
@chenghuaWang chenghuaWang merged commit e2507d4 into UbiquitousLearning:v2 Aug 15, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant