YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
llama.cpp (fork) β Gemma 4 + audio (mtmd)
Source snapshot of the private llama.cpp fork used by AGIWS inference workers.
What is inside
src/models/gemma4.cpp,gemma4-assistant.cppβ text modelsgemma4,gemma4-assistant.tools/mtmd/clip.cppβ graphsclip_graph_gemma4a/clip_graph_gemma4ua(audio encoders).tools/mtmd/mtmd-audio.cppβ preprocessorsgemma4a/gemma4ua, mel filters, streaming.tools/mtmd/mtmd.hβmtmd_support_audio,mtmd_bitmap_init_from_audio.tools/serverβ OpenAI-compatible server acceptinginput_audiocontent parts.conversion/gemma.pyβGemma4ModelGGUF converter (Gemma4ForConditionalGeneration).
Files
src/llama-cpp-src.tar.gzβ full source tree (no.git, no build artifacts).lib/*.soβ prebuilt CUDA libraries andllama-serverfor T4 (sm_75), uploaded by the build job.lib/BUILD_INFO.txtβ compiler, CUDA version, git-less snapshot hash, sha256 of every artifact.
Build (Colab T4)
tar -xzf src/llama-cpp-src.tar.gz -C /content/llama-cpp-fork
cmake -S /content/llama-cpp-fork -B /content/llama-cpp-fork/build \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_CUDA=ON \
-DGGML_NATIVE=OFF \
-DCMAKE_CUDA_ARCHITECTURES=75 \
-DBUILD_SHARED_LIBS=ON \
-DLLAMA_CURL=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF
cmake --build /content/llama-cpp-fork/build -j"$(nproc)" --target llama-server
Artifacts needed at runtime: llama-server plus libllama.so*, libmtmd.so*, libggml*.so*
(libggml-base, libggml-cpu, libggml-cuda, libggml).
Runtime flags for Gemma audio:
LD_LIBRARY_PATH=/content/llama/lib \
/content/llama/lib/llama-server -m .../gemma-4-12b-it-Q4_K_M.gguf \
--mmproj .../mmproj-F16.gguf -ngl 99 -c 4096 --host 127.0.0.1 --port 8091
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support