Source sglang and Megatron-LM from third_party submodules in docker build

.github/workflows/docker-build.yml

@@ -6,6 +6,8 @@ on:
       - main
     paths:
       - 'docker/Dockerfile'
+      - 'third_party/sglang'
+      - 'third_party/Megatron-LM'
 
   schedule:
     # Every 12 hours: midnight and noon UTC
@@ -118,6 +120,21 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      # The submodules under third_party/ are gitfile-linked (`.git` is a file
+      # pointing at <outer>/.git/modules/...), which Docker COPY would carry
+      # into the image as a dangling reference. Replace each gitlink with the
+      # SHA the submodule points at, then drop the gitlink itself — the image
+      # only needs the source tree, not git history.
+      - name: Strip submodule .git pointers for Docker COPY
+        run: |
+          set -eux
+          for sub in third_party/sglang third_party/Megatron-LM; do
+            git -C "$sub" rev-parse HEAD > "$sub/.miles-submodule-sha"
+            rm -f "$sub/.git"
+          done
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3

.gitmodules

@@ -6,3 +6,11 @@
 	path = examples/experimental/swe-agent/mini-swe-agent
 	url = https://github.com/yueming-yuan/nv-mini-swe-agent
 	branch = miles-swe-agent
+[submodule "third_party/sglang"]
+	path = third_party/sglang
+	url = git@github.com:sgl-project/sglang.git
+	branch = sglang-miles
+[submodule "third_party/Megatron-LM"]
+	path = third_party/Megatron-LM
+	url = git@github.com:radixark/Megatron-LM.git
+	branch = miles-main

docker/Dockerfile

@@ -15,12 +15,10 @@ ARG SGLANG_IMAGE_TAG=v0.5.10
 FROM lmsysorg/sglang:${SGLANG_IMAGE_TAG} AS sglang
 
 # ======================================== Arguments =============================================
-
-ARG SGLANG_BRANCH=sglang-miles
-ARG SGLANG_COMMIT=""
-
-ARG MEGATRON_REPO=radixark/Megatron-LM
-ARG MEGATRON_BRANCH=miles-main
+#
+# sglang and Megatron-LM are pulled from the miles repo's git submodules
+# under third_party/, so their versions are recorded by the submodule
+# pointers rather than by branch/commit build args.
 
 ARG ENABLE_CUDA_13=0
 
@@ -105,9 +103,8 @@ RUN if [ "${ENABLE_CUDA_13}" = "1" ] && [ -d /tmp/patches/cu13 ]; then \
 # apex
 RUN pip install /tmp/wheels/apex-*.whl
 
-RUN git clone https://github.com/${MEGATRON_REPO}.git --recursive -b ${MEGATRON_BRANCH} Megatron-LM && \
-    cd Megatron-LM && \
-    pip install -e .
+COPY third_party/Megatron-LM /root/Megatron-LM
+RUN cd /root/Megatron-LM && pip install -e .
 
 RUN pip install git+https://github.com/fzyzcjy/torch_memory_saver.git@d64a639 --no-cache-dir --force-reinstall
 # RUN pip install git+https://github.com/fzyzcjy/Megatron-Bridge.git@dev_rl --no-build-isolation
@@ -133,15 +130,15 @@ RUN rm -rf /root/.cache/pip /root/flash-attention
 
 # ====================================== Install sglang-miles ============================================
 
-# Install sglang from sglang-miles branch
-RUN cd /sgl-workspace/sglang && \
-    git fetch origin ${SGLANG_BRANCH} && \
-    if [ -n "${SGLANG_COMMIT}" ]; then \
-      git checkout ${SGLANG_COMMIT}; \
-    else \
-      git checkout FETCH_HEAD; \
-    fi && \
-    pip install -e "python[all]" --no-deps
+# Overlay the sglang source from the third_party/sglang submodule onto the
+# base image's /sgl-workspace/sglang directory. The submodule pointer is
+# the source of truth for which sglang revision the image carries. The
+# base image ships a stale `.git/` dir at this path — drop it before COPY
+# so the resulting image isn't carrying a git index that disagrees with
+# the working tree.
+RUN rm -rf /sgl-workspace/sglang/.git
+COPY third_party/sglang /sgl-workspace/sglang
+RUN cd /sgl-workspace/sglang && pip install -e "python[all]" --no-deps
 
 # ====================================== Install main package ============================================