llama.cpp
5ca49cbe - ggml: implement quantized KV cache for FA (#7372)

Commit

1 year ago

ggml: implement quantized KV cache for FA (#7372)

References

#7372 - ggml: implement quantized KV cache for FA

Author

JohannesGaessler

JohannesGaessler

Parents

Files1

ggml.c