The Wayback Machine - https://web.archive.org/web/20230313023907/https://github.com/ggerganov/llama.cpp/pulls
Skip to content

Pull requests: ggerganov/llama.cpp

Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Assignee
Filter by who’s assigned
Sort

Pull requests list

Initial support for CMake
#75 opened Mar 13, 2023 by etra0 Draft
Misc: Use argparse
#72 opened Mar 13, 2023 by Dietr1ch Loading…
Misc: Make the conversion script executable
#68 opened Mar 13, 2023 by Dietr1ch Loading…
Use vdotq_s32 to improve performance
#67 opened Mar 12, 2023 by ggerganov Loading…
Add sentencepiece tokenizer and modify build
#66 opened Mar 12, 2023 by beiller Loading…
Reduce model loading time
#43 opened Mar 12, 2023 by maekawatoshiki Loading…
Nix flake
#40 opened Mar 12, 2023 by niklaskorz Draft
Port to Visual C++.
#36 opened Mar 12, 2023 by jaykrell Loading…
Add oneliner for batch quantization
#17 opened Mar 11, 2023 by jooray Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.