mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 23:09:53 +00:00
7d1a378b8f
* CUDA: refactor mmq, dmmv, mmvq * fix out-of-bounds write * struct for qk, qr, qi * fix cmake build * mmq_type_traits
6 lines
179 B
Plaintext
6 lines
179 B
Plaintext
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
|
|
|
|
#include "../fattn-vec-f16.cuh"
|
|
|
|
DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0);
|