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

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

CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014)

* CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID

* fix logic for RoPE support, CUDA graphs

Packaging of ggml-org/llama.cpp

ggml/src/ggml-cuda/ggml-cuda.cu		diff \| blob \| history
ggml/src/ggml-cuda/mmv.cu		diff \| blob \| history
ggml/src/ggml-cuda/mmv.cuh		diff \| blob \| history
ggml/src/ggml-cuda/mmvq.cu		diff \| blob \| history
ggml/src/ggml-cuda/mmvq.cuh		diff \| blob \| history
ggml/src/ggml-cuda/quantize.cu		diff \| blob \| history
ggml/src/ggml-cuda/quantize.cuh		diff \| blob \| history
ggml/src/ggml-cuda/vecdotq.cuh		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history