llama.cpp
3f460a2b - cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)

Commit

2 years ago

cuda : add RoPE kernel for mode == 2 (NeoX) (#2760) * cuda : add RoPE kernel for mode == 2 (NeoX) * falcon : do not offload the embeddings layer

References

Author

ggerganov

Parents