# see docs/operations.md#speed-bench
FROM python:3.12-slim
ARG LLAMA_CPP_REF=0ec4027a2a0183de87c007069adddc06e665f7de
ADD https://raw.githubusercontent.com/ggml-org/llama.cpp/${LLAMA_CPP_REF}/tools/server/bench/speed-bench/requirements.txt \
    https://raw.githubusercontent.com/ggml-org/llama.cpp/${LLAMA_CPP_REF}/tools/server/bench/speed-bench/speed_bench.py \
    https://raw.githubusercontent.com/ggml-org/llama.cpp/${LLAMA_CPP_REF}/tools/server/bench/speed-bench/speed_bench_compare.py \
    /app/
RUN pip install --no-cache-dir -r /app/requirements.txt
WORKDIR /results