--cpu-strict -np 2

Dockerfile

@@ -4,7 +4,7 @@ FROM ghcr.io/ggml-org/llama.cpp:server
 WORKDIR /app
 
 RUN apt update && apt install -y python3 python3-pip python3-venv pipx
-ENV PATH="/root/.local/bin:$PATH"
+ENV PATH=/root/.local/bin:$PATH
 
 # RUN pip install huggingface_hub --break-system-packages
 RUN pipx install huggingface_hub
@@ -13,10 +13,11 @@ RUN pipx install huggingface_hub
 RUN hf download prism-ml/Bonsai-8B-gguf Bonsai-8B.gguf --local-dir /app
 RUN mv /app/Bonsai-8B.gguf /app/bonsai-8b
 
-#MD ["--server", \
+# CMD ["--server", \
 CMD ["--model", "/app/bonsai-8b", \
      "--host", "0.0.0.0", \
      "--port", "7860", \
+     "--cpu-strict", "-np", "2" \
      "-t", "2", \
      "--cache-type-k", "q8_0", \
      "--cache-type-v", "iq4_nl", \

README.md

@@ -1,5 +1,5 @@
 ---
-title: bonsai-b
+title: bonsai-8b
 emoji: 💻
 colorFrom: purple
 colorTo: blue