integrate llama.cpp for local inference

2025-07-12 12:22:05 -07:00
parent 57133f3d2c
commit f319cce82a
6 changed files with 227 additions and 0 deletions
@@ -0,0 +1,3 @@
+[submodule "stream/thirdparty/llama.cpp"]
+	path = stream/thirdparty/llama.cpp
+	url = https://github.com/ggml-org/llama.cpp