We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
ggml : fix IQ3_XXS on Metal (ggml-org#5219) Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
llama : apply classifier-free guidance to logits directly (ggml-org#4951 )
CUDA: faster dequantize kernels for Q4_0 and Q4_1 (ggml-org#4938) Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
sync : ggml