CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
- Published
- Source
- arXiv
- Paper number
- 194
- Field
- Machine Learning
- arXiv ID
- 2605.19269
Key points
- It maintains local state for operations such as the online log-sum-exp used in cross-entropy loss.
- It recovers a substantial portion of GPU time that would otherwise be lost to data movement.
- It provides a structured DSL that simplifies writing high-performance kernels.
Paper links
External research summaries. These are not HDATF publications or measured product results.