llama.cpp
dee2a846 - ggml : adjust logic for offloading ops to weight's backend (#25832)

Commit

29 days ago

ggml : adjust logic for offloading ops to weight's backend (#25832) * ggml : adjust logic for offloading ops to weight's backend * llama : dsv4 graph fixes

References

#25832 - ggml : adjust logic for offloading ops to weight's backend

Author

ggerganov

Parents

7ef790f9

llama.cpp dee2a846 - ggml : adjust logic for offloading ops to weight's backend (#25832)

llama.cpp
dee2a846 - ggml : adjust logic for offloading ops to weight's backend (#25832)