From c85e139c68b0b0b15656cc0bc9618d632ed18822 Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Sun, 28 Jul 2024 19:43:18 +0300 Subject: iq2_k: Basics Quantize/dequantize, CUDA deqantize, AVX512 iqk_mul_mat. --- ggml/src/ggml-cuda.cu | 1 + 1 file changed, 1 insertion(+) (limited to 'ggml/src/ggml-cuda.cu') 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; -- cgit v1.2.3