Repository navigation

Commit 9d5f6bc

authored

Pin llama.cpp for the native GGML engine (#23929)

Summary: Add `ggml-org/llama.cpp` under `backends/native/third-party`, pinned to `620d2225cc436ab0b001e3200e590e3b286ef9ab`, matching the internal dependency. The full submodule retains the upstream license and copyright notices. Authored with AI assistance from Codex. Reviewed By: digantdesai Differential Revision: D125694754 Pull Request resolved: #23929

1 parent fd9c7d2 commit 9d5f6bcCopy full SHA for 9d5f6bc

2 files changed

.gitmodules
backends/native/third-party
- llama.cpp

`‎.gitmodules‎`

-Original file line number
+Diff line change
 	path = backends/mlx/third-party/mlx
 	url = https://github.com/ml-explore/mlx.git
 	shallow = true
 +[submodule "backends/native/third-party/llama.cpp"]
 +	path = backends/native/third-party/llama.cpp
 +	url = https://github.com/ggml-org/llama.cpp.git

`‎backends/native/third-party/llama.cpp‎`

Submodule llama.cpp added at 620d222

Comments

(0)