GGitHubAdd CUDA 13.4 support (#601)
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
Aligning GroupedGemm trait with other cublas traits (#510) * GroupedGemm takes DevicePtr/DevicePtrMut * Add safety section * Clippy | 9 个月前 | |
Add CUDA 13.4 support (#601) * Add CUDA 13.4 support * Generated bindings: cuda-13040 * Non-generated support code for cuda-13040 Generated from redistrib_13.4.2 (latest 13.4.x patch manifest). Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * Fix formatting for cuda-13040 cfg gates Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> | 2 天前 | |
Load symbol on use instead of at initialization (#573) * Lazy load symbols on use instead of at initialization * Tidy * Regenerate bindings * Fix missing braces on extern c functions * Adding rustfmt::skip to bindings * Move rustfmt::skip to mod level | 4 个月前 | |
cublas Grouped gemm (#508) * cuBLAS Grouped GEMM support (#499) * wip: initial grouped gemm * fix cublas test syntax error * cublas: make gmm generic over f16/bf16 * gmm tests: move half imports behind feature guard * Cleanup on grouped_gemm * More grouped gemm updates & tests pass * Adding feature gates to grouped gemm * Reorg featuer gate to reduce warnings * Reduce more warnings --------- Co-authored-by: Zack Angelo <zackangelo@gmail.com> | 9 个月前 |