Spaces:

ggml-org
/

gguf-my-repo

Running on A10G

freddyaboulton HF staff commited on Apr 8, 2024

Commit

e9c1530

verified ·

1 Parent(s): db1b986

Update to version 4.26.0 to fix slow load time

Version 4.25.0 had a sub-optimal implementation of one of the server routes that caused slow load times. 4.26.0 fixes this.

Files changed (1) hide show

Dockerfile CHANGED Viewed

@@ -37,7 +37,7 @@ RUN pyenv install ${PYTHON_VERSION} && \
     pyenv global ${PYTHON_VERSION} && \
     pyenv rehash && \
     pip install --no-cache-dir -U pip setuptools wheel && \
-    pip install "huggingface-hub" "hf-transfer" "gradio"
 COPY --chown=1000 . ${HOME}/app
 RUN git clone https://github.com/ggerganov/llama.cpp

     pyenv global ${PYTHON_VERSION} && \
     pyenv rehash && \
     pip install --no-cache-dir -U pip setuptools wheel && \
+    pip install "huggingface-hub" "hf-transfer" "gradio>=4.26.0"
 COPY --chown=1000 . ${HOME}/app
 RUN git clone https://github.com/ggerganov/llama.cpp