git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

CUDA: add Q2_0 support (#25707)

20 files changed:

ggml/src/ggml-cuda/common.cuh		diff \| blob \| history
ggml/src/ggml-cuda/convert.cu		diff \| blob \| history
ggml/src/ggml-cuda/dequantize.cuh		diff \| blob \| history
ggml/src/ggml-cuda/getrows.cu		diff \| blob \| history
ggml/src/ggml-cuda/ggml-cuda.cu		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-ampere.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-cdna.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-pascal.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-rdna2.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-rdna3-5.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-rdna3.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-config-rdna4.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq-load-tiles.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmq.cu		diff \| blob \| history
ggml/src/ggml-cuda/mmq.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmvq.cu		diff \| blob \| history
ggml/src/ggml-cuda/template-instances/generate_cu_files.py		diff \| blob \| history
ggml/src/ggml-cuda/template-instances/mmq-instance-q2_0.cu	[new file with mode: 0644]	blob
ggml/src/ggml-cuda/vecdotq.cuh		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history

Packaging of ggml-org/llama.cpp