Skip to content

CUDA: fix quantized KV cache + multiple sequences#14822

Merged
JohannesGaessler merged 2 commits intoggml-org:gg/tests-fa-non-contfrom
JohannesGaessler:cuda-fa-nc-quant
Jul 23, 2025
Merged

CUDA: fix quantized KV cache + multiple sequences#14822
JohannesGaessler merged 2 commits intoggml-org:gg/tests-fa-non-contfrom
JohannesGaessler:cuda-fa-nc-quant

Commits

Commits on Jul 22, 2025

Commits on Jul 23, 2025