diff --git a/docker/Dockerfile b/docker/Dockerfile index cec05825d..264397f85 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -41,26 +41,26 @@ RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \ && cd sglang \ && if [ "$BUILD_TYPE" = "srt" ]; then \ if [ "$CUDA_VERSION" = "12.1.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "12.4.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "12.5.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "11.8.0" ]; then \ - python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu118/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer/; \ python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \ else \ echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \ fi; \ else \ if [ "$CUDA_VERSION" = "12.1.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "12.4.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "12.5.1" ]; then \ - python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/; \ elif [ "$CUDA_VERSION" = "11.8.0" ]; then \ - python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu118/torch2.4/flashinfer/; \ + python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer/; \ python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \ else \ echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \ diff --git a/docs/start/install.md b/docs/start/install.md index fc1a936c6..38bce59f0 100644 --- a/docs/start/install.md +++ b/docs/start/install.md @@ -6,7 +6,7 @@ You can install SGLang using any of the methods below. ``` pip install --upgrade pip pip install sgl-kernel --force-reinstall --no-deps -pip install "sglang[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/ +pip install "sglang[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/ ``` Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/installation.html) to install the proper version according to your PyTorch and CUDA versions. @@ -19,7 +19,7 @@ cd sglang pip install --upgrade pip pip install sgl-kernel --force-reinstall --no-deps -pip install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/ +pip install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer/ ``` Note: Please check the [FlashInfer installation doc](https://docs.flashinfer.ai/installation.html) to install the proper version according to your PyTorch and CUDA versions. If you meet with issue like **ImportError: cannot import name `_grouped_size_compiled_for_decode_kernels`**, installing FlashInfer with some older version like 0.1.6 instead of the latest version could solve it.