llama.cpp
1215ed7d - CUDA: Implemented row flattening for non-glm RoPE (#2468)

Commit

2 years ago

CUDA: Implemented row flattening for non-glm RoPE (#2468)

References

#2468 - CUDA: Implemented row flattening for non-glm RoPE

Author

JohannesGaessler

JohannesGaessler

Parents

Loading