diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-07-28 19:43:18 +0300 |
|---|---|---|
| committer | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-08-01 09:38:06 +0200 |
| commit | c85e139c68b0b0b15656cc0bc9618d632ed18822 (patch) | |
| tree | f07e1f8c59522d286301c45de78d52ba48353ac4 /ggml/src/ggml-cuda/common.cuh | |
| parent | 291066e6df5318c322a03e592483aae8820d3b19 (diff) | |
iq2_k: Basics
Quantize/dequantize, CUDA deqantize, AVX512 iqk_mul_mat.
Diffstat (limited to 'ggml/src/ggml-cuda/common.cuh')
| -rw-r--r-- | ggml/src/ggml-cuda/common.cuh | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh index 8549c4e5..12eebb00 100644 --- a/ggml/src/ggml-cuda/common.cuh +++ b/ggml/src/ggml-cuda/common.cuh @@ -670,6 +670,13 @@ struct ggml_cuda_type_traits<GGML_TYPE_IQ4_XS> { }; template<> +struct ggml_cuda_type_traits<GGML_TYPE_IQ2_K> { + static constexpr int qk = QK_K; + static constexpr int qr = QR4_XS; + static constexpr int qi = QI4_XS; +}; + +template<> struct ggml_cuda_type_traits<GGML_TYPE_IQ4_K> { static constexpr int qk = QK_K; static constexpr int qr = QR4_XS; |