mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-01 12:09:54 +00:00
0ceeb11721
* Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
7 lines
297 B
Python
7 lines
297 B
Python
# pyright: reportUnusedImport=false
|
|
|
|
from .gguf_convert_endian import main as gguf_convert_endian_entrypoint
|
|
from .gguf_dump import main as gguf_dump_entrypoint
|
|
from .gguf_set_metadata import main as gguf_set_metadata_entrypoint
|
|
from .gguf_new_metadata import main as gguf_new_metadata_entrypoint
|