diff --git a/docker/Dockerfile b/docker/Dockerfile index 6dd4f9fbb..437af6bc0 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -18,6 +18,9 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \ && rm -rf /var/lib/apt/lists/* \ && apt clean +# For openbmb/MiniCPM models +RUN pip3 install datamodel_code_generator + WORKDIR /sgl-workspace RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \ diff --git a/python/sglang/srt/model_executor/cuda_graph_runner.py b/python/sglang/srt/model_executor/cuda_graph_runner.py index bf7d89080..3f73e734d 100644 --- a/python/sglang/srt/model_executor/cuda_graph_runner.py +++ b/python/sglang/srt/model_executor/cuda_graph_runner.py @@ -150,7 +150,7 @@ class CudaGraphRunner: f"Capture cuda graph failed: {e}\n" "Possible solutions:\n" "1. disable cuda graph by --disable-cuda-graph\n" - "2. set --mem-fraction-static to a smaller value\n" + "2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n" "3. disable torch compile by not using --enable-torch-compile\n" "Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose \n" )