12 commits

Author	SHA1	Message	Date
Seunghoon Lee	d7714d84c0	Add support of ROCm 6. (#27) ... * Add support of ROCm 6.1.2 for Windows. * Fix CI. * Use llvm.sqrt.f64.	2024-07-13 13:47:35 +09:00
Seunghoon Lee	4baac34d4e	Implement cublasDotEx.	2024-04-10 15:20:58 +09:00
Seunghoon Lee	0f191c2354	Fix type errors.	2024-03-25 14:09:02 +09:00
Seunghoon Lee	1122cc0e83	Implement cublasSdot.	2024-03-25 11:30:23 +09:00
Seunghoon Lee	cd1e0a3d50	Implement cublasDgetrsBatched.	2024-03-18 22:38:57 +09:00
Seunghoon Lee	2aa6fa3491	Implement cublasDgemm.	2024-02-23 21:57:52 +09:00
Seunghoon Lee	d325f6a43c	Enable build for Linux.	2024-02-18 23:38:55 +09:00
Seunghoon Lee	ad970a7665	Implement cublasSgetrsBatched.	2024-02-18 21:34:25 +09:00
Seunghoon Lee	8f3c1292b0	Merge remote-tracking branch 'upstream/master'	2024-02-17 04:13:06 +09:00
Andrzej Janik	4a81dbffb5	Update llama.cpp support (#102) ... Add sign extension support to prmt, allow set.<op>.f16x2.f16x2, add more BLAS mappings	2024-02-16 00:01:21 +01:00
Seunghoon Lee	1ef7ef3938	Add support of cuBLAS, cuSPARSE for Windows.	2024-02-15 06:54:21 +09:00
Andrzej Janik	1b9ba2b233	Nobody expects the Red Team ... Too many changes to list, but broadly: * Remove Intel GPU support from the compiler * Add AMD GPU support to the compiler * Remove Intel GPU host code * Add AMD GPU host code * More device instructions. From 40 to 68 * More host functions. From 48 to 184 * Add proof of concept implementation of OptiX framework * Add minimal support of cuDNN, cuBLAS, cuSPARSE, cuFFT, NCCL, NVML * Improve ZLUDA launcher for Windows	2024-02-11 20:45:51 +01:00