Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

llama.cpp 2950 (New formula) #172186

Closed
wants to merge 9 commits into from
Closed

llama.cpp 2950 (New formula) #172186

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
d08feb7
llama.cpp 2950 (New formula)
Vaibhavs10 May 20, 2024
dd9ad47
llama.cpp 2960 (New Formula) Fix failing test.
Vaibhavs10 May 20, 2024
6bddbf1
llama.cpp 2960 (New Formula) Fix error.
Vaibhavs10 May 24, 2024
86c25fa
llama.cpp 2960 (New Formula) Fix error.
Vaibhavs10 May 24, 2024
8e4099e
Update Formula/l/llama.cpp.rb
Vaibhavs10 May 25, 2024
764c468
llama.cpp 2960 (New Formula) Suggestions.
Vaibhavs10 May 25, 2024
4240e05
Update llama.cpp.rb
Vaibhavs10 May 25, 2024
a385214
Update llama.cpp.rb
Vaibhavs10 May 25, 2024
6661795
llama.cpp 2960 (New Formula) Formatting.
Vaibhavs10 May 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .github/autobump.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1344,6 +1344,7 @@ literate-git
little-cms2
livekit
livekit-cli
llama-cpp
llm
llvm
lmdb
Expand Down
31 changes: 31 additions & 0 deletions Formula/l/llama.cpp.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
class LlamaCpp < Formula
desc "LLM inference in C/C++"
homepage "https://github.com/ggerganov/llama.cpp"
# pull from git tag to get submodules
url "https://github.com/ggerganov/llama.cpp.git",
tag: "b2963",
revision: "95fb0aefab568348da159efdd370e064d1b35f97"
license "MIT"

depends_on xcode: ["15.0", :build]
depends_on arch: :arm64
depends_on macos: :ventura
Comment on lines +10 to +12
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Where are these requirements documented?

depends_on :macos
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
depends_on :macos

This doesn't seem correct.


uses_from_macos "curl"

def install
system "make", "LLAMA_FATAL_WARNINGS=ON", "LLAMA_METAL_EMBED_LIBRARY=ON", "LLAMA_CURL=ON"

bin.install "main" => "llama-cli"
bin.install "server" => "llama-server"
end

test do
llama_cli_command = %w[ llama-cli
--hf-repo ggml-org/tiny-llamas
-m stories15M-q4_0.gguf
-n 400 -p I -ngl 0 ]
assert_match "<s>", shell_output(llama_cli_command.join(" "))
end
end
Loading