]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (#15802)
authorJohannes Gäßler <redacted>
Fri, 5 Sep 2025 14:07:02 +0000 (16:07 +0200)
committerGitHub <redacted>
Fri, 5 Sep 2025 14:07:02 +0000 (16:07 +0200)
commit5143fa895e7725c5bd2135daf7d8f793d98fa91c
treef4f0cab35b47cffa6ef3c5cbf4b61e184140bdc2
parent3a550b5ca4565c9e28f63880d47840feb27d0ff6
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (#15802)

* CUDA: fastdiv, launch bounds for mmvq + q8_1 quant
ggml/src/ggml-cuda/common.cuh
ggml/src/ggml-cuda/mmvq.cu
ggml/src/ggml-cuda/quantize.cu