mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-09 20:18:57 +01:00
69c487f4ed
* CUDA: MMQ code deduplication + iquant support * 1 less parallel job for CI build
6 lines
141 B
Plaintext
6 lines
141 B
Plaintext
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
|
|
|
|
#include "../mmq.cuh"
|
|
|
|
DECL_MMQ_CASE(GGML_TYPE_IQ3_XXS);
|