mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +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>
12 lines
524 B
YAML
12 lines
524 B
YAML
blank_issues_enabled: true
|
|
contact_links:
|
|
- name: Got an idea?
|
|
url: https://github.com/ggerganov/llama.cpp/discussions/categories/ideas
|
|
about: Pop it there. It may then become an enhancement ticket.
|
|
- name: Got a question?
|
|
url: https://github.com/ggerganov/llama.cpp/discussions/categories/q-a
|
|
about: Ask a question there!
|
|
- name: Want to contribute?
|
|
url: https://github.com/ggerganov/llama.cpp/wiki/contribute
|
|
about: Head to the contribution guide page of the wiki for areas you can help with
|