diff --git a/backend/Dockerfile b/backend/Dockerfile
index 5213bb00c50..84c90e16f67 100644
--- a/backend/Dockerfile
+++ b/backend/Dockerfile
@@ -4,6 +4,33 @@ ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2
 
 FROM $UV_IMAGE AS uvbin
 
+# ---------- Rust extension ----------
+# Copies only the native build's inputs, so the fat-LTO compile stays cached across Python-only changes
+FROM $LITELLM_BUILD_IMAGE AS rust-native
+
+WORKDIR /app
+USER root
+
+COPY --from=uvbin /uv /uvx /usr/local/bin/
+
+RUN for i in 1 2 3; do \
+      apk add --no-cache bash gcc python-3.13 python-3.13-dev openssl openssl-dev && break; \
+      [ $i = 3 ] && { echo "apk add failed after 3 retries" >&2; exit 1; }; \
+      sleep 5; \
+    done
+
+ENV UV_PYTHON_DOWNLOADS=0
+
+COPY pyproject.toml README.md rust-toolchain.toml ./
+COPY .cargo ./.cargo
+COPY litellm-rust ./litellm-rust
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    mkdir -p litellm/rust_bridge /wheels && \
+    touch litellm/__init__.py litellm/rust_bridge/__init__.py && \
+    uvx --python python3.13 --from maturin==1.15.0 --with puccinialin==0.1.14 \
+        python -c "import maturin; maturin.build_wheel('/wheels')"
+
 # ---------- Builder ----------
 FROM $LITELLM_BUILD_IMAGE AS builder
 
@@ -54,7 +81,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 COPY . .
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --frozen --no-default-groups --no-editable \
+    uv sync --frozen --no-install-project --no-default-groups --no-editable \
         --extra proxy \
         --extra proxy-runtime \
         --group admin-mcp \
@@ -63,6 +90,9 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         --extra saml \
         --python python3.13
 
+RUN --mount=type=bind,from=rust-native,source=/wheels,target=/wheels \
+    uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm-*.whl
+
 RUN cp "$(python -c 'import sysconfig; print(sysconfig.get_paths()["purelib"])')"/litellm/rust_bridge/_native*.so litellm/rust_bridge/
 
 RUN HOME=/opt/prisma XDG_CACHE_HOME=/opt/prisma/.cache PRISMA_BINARY_CACHE_DIR=/opt/prisma/binaries \
diff --git a/gateway/Dockerfile b/gateway/Dockerfile
index ee45f293ef8..051b1c30c8f 100644
--- a/gateway/Dockerfile
+++ b/gateway/Dockerfile
@@ -20,6 +20,33 @@ RUN curl -fsSL -o pgbouncer.tar.gz "https://www.pgbouncer.org/downloads/files/${
     make -j"$(nproc)" pgbouncer && \
     install -m 0755 pgbouncer /usr/local/bin/pgbouncer
 
+# ---------- Rust extension ----------
+# Copies only the native build's inputs, so the fat-LTO compile stays cached across Python-only changes
+FROM $LITELLM_BUILD_IMAGE AS rust-native
+
+WORKDIR /app
+USER root
+
+COPY --from=uvbin /uv /uvx /usr/local/bin/
+
+RUN for i in 1 2 3; do \
+      apk add --no-cache bash gcc python-3.13 python-3.13-dev openssl openssl-dev && break; \
+      [ $i = 3 ] && { echo "apk add failed after 3 retries" >&2; exit 1; }; \
+      sleep 5; \
+    done
+
+ENV UV_PYTHON_DOWNLOADS=0
+
+COPY pyproject.toml README.md rust-toolchain.toml ./
+COPY .cargo ./.cargo
+COPY litellm-rust ./litellm-rust
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    mkdir -p litellm/rust_bridge /wheels && \
+    touch litellm/__init__.py litellm/rust_bridge/__init__.py && \
+    uvx --python python3.13 --from maturin==1.15.0 --with puccinialin==0.1.14 \
+        python -c "import maturin; maturin.build_wheel('/wheels')"
+
 # ---------- Builder ----------
 FROM $LITELLM_BUILD_IMAGE AS builder
 
@@ -66,11 +93,11 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         --extra bedrock-realtime \
         --python python3.13
 
-# Stage 2 — copy source and install the project + workspace members.
+# Stage 2 — copy source and install the workspace members.
 COPY . .
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --frozen --no-default-groups --no-editable \
+    uv sync --frozen --no-install-project --no-default-groups --no-editable \
         --extra proxy \
         --extra proxy-runtime \
         --group admin-mcp \
@@ -79,6 +106,9 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         --extra bedrock-realtime \
         --python python3.13
 
+RUN --mount=type=bind,from=rust-native,source=/wheels,target=/wheels \
+    uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm-*.whl
+
 # PYTHONPATH=/app makes the source tree shadow the installed package, so the
 # compiled Rust extension must live next to the source or it is never imported.
 RUN cp "$(python -c 'import sysconfig; print(sysconfig.get_paths()["purelib"])')"/litellm/rust_bridge/_native*.so litellm/rust_bridge/
diff --git a/migrations/Dockerfile b/migrations/Dockerfile
index 255b94b0ea8..b39a9bfa9bf 100644
--- a/migrations/Dockerfile
+++ b/migrations/Dockerfile
@@ -24,6 +24,32 @@ FROM $UV_IMAGE AS uvbin
 # under nodeenv. Crucially we do NOT run `prisma generate` at RUNTIME; the
 # old migration job did, on every pod start, which is the wasteful behaviour
 # the componentization is fixing.
+# Copies only the native build's inputs, so the fat-LTO compile stays cached across Python-only changes
+FROM $LITELLM_BUILD_IMAGE AS rust-native
+
+WORKDIR /app
+USER root
+
+COPY --from=uvbin /uv /uvx /usr/local/bin/
+
+RUN for i in 1 2 3; do \
+      apk add --no-cache bash gcc python-3.13 python-3.13-dev openssl openssl-dev && break; \
+      [ $i = 3 ] && { echo "apk add failed after 3 retries" >&2; exit 1; }; \
+      sleep 5; \
+    done
+
+ENV UV_PYTHON_DOWNLOADS=0
+
+COPY pyproject.toml README.md rust-toolchain.toml ./
+COPY .cargo ./.cargo
+COPY litellm-rust ./litellm-rust
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    mkdir -p litellm/rust_bridge /wheels && \
+    touch litellm/__init__.py litellm/rust_bridge/__init__.py && \
+    uvx --python python3.13 --from maturin==1.15.0 --with puccinialin==0.1.14 \
+        python -c "import maturin; maturin.build_wheel('/wheels')"
+
 FROM $LITELLM_BUILD_IMAGE AS builder
 
 WORKDIR /app
@@ -58,15 +84,18 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         --extra extra_proxy \
         --python python3.13
 
-# Stage 2 — copy source and install the project + workspace members.
+# Stage 2 — copy source and install the workspace members.
 COPY . .
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --frozen --no-default-groups --no-editable \
+    uv sync --frozen --no-install-project --no-default-groups --no-editable \
         --extra proxy \
         --extra extra_proxy \
         --python python3.13
 
+RUN --mount=type=bind,from=rust-native,source=/wheels,target=/wheels \
+    uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm-*.whl
+
 RUN cp "$(python -c 'import sysconfig; print(sysconfig.get_paths()["purelib"])')"/litellm/rust_bridge/_native*.so litellm/rust_bridge/
 
 COPY migrations/run.py /app/run.py