diff options
| author | LostRuins <39025047+LostRuins@users.noreply.github.com> | 2023-06-29 11:56:43 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-29 05:56:43 +0200 |
| commit | 96a712ca1b7f427e3bd7ffc0c70b2105cfc7fbf1 (patch) | |
| tree | 448ac4c00677b54d68272bc4f5310bc5ebe85f02 /ggml-opencl.h | |
| parent | d3494bb86bf7ad5b0b60aae0220ea576f273b5c0 (diff) | |
Porting the improved K-Quant CUDA kernels to OpenCL (#1966)
* Added broken new q4k quant
* xx + ib0
* Fix q2_k fast kernel
* Use preprocessor for QK_K
* Add q6_k fast matmul kernel
* ported q3k speedup successfully
* ported q2k and q5k speedups
* remove old dot kernels and template
* fixed global const struct types
* fixing address spaces
* fixed string too long CI issue
---------
Co-authored-by: 0cc4m <picard12@live.de>
Diffstat (limited to 'ggml-opencl.h')
0 files changed, 0 insertions, 0 deletions