diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-06-05 19:13:51 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-05 19:13:51 +0300 |
| commit | eded4e20d4decdc6e8c18e645fd1db0833ad251d (patch) | |
| tree | b97f31f30d263b3d2ca610d75bcdd58793f7e04d /ggml/src/ggml-cuda.cu | |
| parent | 8ffad187abbb93b74db8ef813b6fdceec80e02b0 (diff) | |
IQ1_M_R4 CUDA implementation (#494)
* iq1_m_r4: CUDA dequantize
* iq1_m_r4: CUDA dequantize
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
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 de9816fe..6bdeb465 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -3477,6 +3477,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons case GGML_TYPE_IQ5_K_R4: case GGML_TYPE_IQ5_KS_R4: case GGML_TYPE_IQ1_S_R4: + case GGML_TYPE_IQ1_M_R4: return true; default: return false; |