llama.cpp
ed8c2615 - cuda : add support for f16->f16 GGML_OP_SET_ROWS (#25367)

Commit

11 days ago

cuda : add support for f16->f16 GGML_OP_SET_ROWS (#25367)

References

#25367 - cuda : add support for f16->f16 GGML_OP_SET_ROWS

Author

fairydreaming

fairydreaming

Parents

Loading