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.cu | |
| parent | 291066e6df5318c322a03e592483aae8820d3b19 (diff) | |
iq2_k: Basics
Quantize/dequantize, CUDA deqantize, AVX512 iqk_mul_mat.
Diffstat (limited to 'ggml/src/ggml-cuda.cu')
| -rw-r--r-- | ggml/src/ggml-cuda.cu | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu index cfeda744..a4c93ad6 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -2754,6 +2754,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: case GGML_TYPE_IQ4_K: + case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ1_BN: case GGML_TYPE_IQ2_BN: return true; |