From 24d59d8d748b20c1bc0fe678c652f999d0d80623 Mon Sep 17 00:00:00 2001
From: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Date: Mon, 13 Jul 2026 04:50:41 +0800
Subject: [PATCH] Fix CUDA 12 Docker dependency resolution (#30858)

---
 docker/Dockerfile | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 74319e82b..628196c54 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -239,6 +239,11 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     && echo '__version__ = "0.0.0"' > sglang/version.py \
     && touch README.md \
     && touch LICENSE \
+    && if [ "${CUDA_VERSION%%.*}" = "12" ]; then \
+           sed -i 's/cuda-python>=13\.0/cuda-python>=12,<13/' pyproject.toml && \
+           sed -i 's/flashinfer_python\[cu13\]/flashinfer_python[cu12]/' pyproject.toml && \
+           sed -i 's/nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' pyproject.toml; \
+       fi \
     && python3 -m pip install --extra-index-url https://download.pytorch.org/whl/cu${CUINDEX} ".[${BUILD_TYPE}]" \
     && if [ "${CUDA_VERSION%%.*}" = "12" ]; then \
            pip list --format=freeze | awk -F'==' '/-cu13(==|$)/ {print $1}' \
@@ -669,6 +674,11 @@ RUN if [ "$BRANCH_TYPE" = "local" ]; then \
 # Clean up __pycache__/tests/pyc in same RUN to avoid writing ~28k files to layer
 RUN --mount=type=cache,target=/root/.cache/pip \
     cd /sgl-workspace/sglang \
+    && if [ "${CUDA_VERSION%%.*}" = "12" ]; then \
+           sed -i 's/cuda-python>=13\.0/cuda-python>=12,<13/' python/pyproject.toml && \
+           sed -i 's/flashinfer_python\[cu13\]/flashinfer_python[cu12]/' python/pyproject.toml && \
+           sed -i 's/nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' python/pyproject.toml; \
+       fi \
     && python3 -m pip install --no-deps -e "python[${BUILD_TYPE}]" \
     && kernels lock python \
     && ( success=0; \