From 01a26544a3547c5d454581f1890d7a9805f388a9 Mon Sep 17 00:00:00 2001 From: Hubert Lu <55214931+hubertlu-tw@users.noreply.github.com> Date: Tue, 30 Sep 2025 20:00:37 -0700 Subject: [PATCH] [AMD] Add Tilelang and Fast Hadamard Transform builds to Dockerfile.rocm (#11114) --- docker/Dockerfile.rocm | 93 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 90 insertions(+), 3 deletions(-) diff --git a/docker/Dockerfile.rocm b/docker/Dockerfile.rocm index d4378236a..001c2ccd3 100644 --- a/docker/Dockerfile.rocm +++ b/docker/Dockerfile.rocm @@ -69,6 +69,13 @@ ARG LLVM_COMMIT="6520ace8227ffe2728148d5f3b9872a870b0a560" ARG MOONCAKE_REPO="https://github.com/kvcache-ai/Mooncake.git" ARG MOONCAKE_COMMIT="dcdf1c784b40aa6975a8ed89fe26321b028e40e8" +ARG TILELANG_REPO="https://github.com/HaiShaw/tilelang.git" +ARG TILELANG_BRANCH="dsv32-mi35x" +ARG TILELANG_COMMIT="ae938cf885743f165a19656d1122ad42bb0e30b8" + +ARG FHT_REPO="https://github.com/jeffdaily/fast-hadamard-transform.git" +ARG FHT_BRANCH="rocm" +ARG FHT_COMMIT="46efb7d776d38638fc39f3c803eaee3dd7016bd1" USER root # Install some basic utilities @@ -90,8 +97,6 @@ RUN if [ "$BUILD_LLVM" = "1" ]; then \ && make -j$(nproc); \ fi -# ----------------------- - # ----------------------- # AITER RUN pip uninstall -y aiter @@ -155,7 +160,6 @@ RUN if [ "$BUILD_MOONCAKE" = "1" ]; then \ make -j "$(nproc)" && make install; \ fi - # ----------------------- # Build SGLang ARG BUILD_TYPE=all @@ -207,6 +211,89 @@ RUN python3 -m pip install --no-cache-dir setuptools-rust \ && python3 -m pip install --no-cache-dir . \ && rm -rf /root/.cache +# ----------------------- +# TileLang +ENV DEBIAN_FRONTEND=noninteractive +ENV LIBGL_ALWAYS_INDIRECT=1 +RUN echo "LC_ALL=en_US.UTF-8" >> /etc/environment + +RUN /bin/bash -lc 'set -euo pipefail; \ + # Build TileLang only for gfx950 + if [ "${GPU_ARCH:-}" != "gfx950" ]; then \ + echo "[TileLang] Skipping (GPU_ARCH=${GPU_ARCH:-unset})"; \ + exit 0; \ + fi; \ + echo "[TileLang] Building TileLang for ${GPU_ARCH}"; \ + \ + # System dependencies (NO llvm-dev to avoid llvm-config-16 shadowing) + apt-get update && apt-get install -y --no-install-recommends \ + build-essential git wget curl ca-certificates gnupg \ + libgtest-dev libgmock-dev \ + libprotobuf-dev protobuf-compiler libgflags-dev libsqlite3-dev \ + python3 python3-dev python3-setuptools python3-pip \ + gcc libtinfo-dev zlib1g-dev libedit-dev libxml2-dev \ + cmake ninja-build pkg-config libstdc++6 \ + && rm -rf /var/lib/apt/lists/*; \ + \ + # Build GoogleTest static libs (Ubuntu package ships sources only) + cmake -S /usr/src/googletest -B /tmp/build-gtest -DBUILD_GTEST=ON -DBUILD_GMOCK=ON -DCMAKE_BUILD_TYPE=Release && \ + cmake --build /tmp/build-gtest -j"$(nproc)" && \ + cp -v /tmp/build-gtest/lib/*.a /usr/lib/x86_64-linux-gnu/ && \ + rm -rf /tmp/build-gtest; \ + \ + # Keep setuptools < 80 (compat with base image) + python3 -m pip install --upgrade "setuptools>=77.0.3,<80" wheel cmake ninja && \ + python3 -m pip cache purge || true; \ + \ + # Locate ROCm llvm-config; fallback to installing LLVM 18 if missing + LLVM_CONFIG_PATH=""; \ + for p in /opt/rocm/llvm/bin/llvm-config /opt/rocm/llvm-*/bin/llvm-config /opt/rocm-*/llvm*/bin/llvm-config; do \ + if [ -x "$p" ]; then LLVM_CONFIG_PATH="$p"; break; fi; \ + done; \ + if [ -z "$LLVM_CONFIG_PATH" ]; then \ + echo "[TileLang] ROCm llvm-config not found; installing LLVM 18..."; \ + curl -fsSL https://apt.llvm.org/llvm.sh -o /tmp/llvm.sh; \ + chmod +x /tmp/llvm.sh; \ + /tmp/llvm.sh 18; \ + LLVM_CONFIG_PATH="$(command -v llvm-config-18)"; \ + if [ -z "$LLVM_CONFIG_PATH" ]; then echo "ERROR: llvm-config-18 not found after install"; exit 1; fi; \ + fi; \ + echo "[TileLang] Using LLVM_CONFIG at: $LLVM_CONFIG_PATH"; \ + export PATH="$(dirname "$LLVM_CONFIG_PATH"):/usr/local/bin:${PATH}"; \ + export LLVM_CONFIG="$LLVM_CONFIG_PATH"; \ + \ + # Optional shim for tools that expect llvm-config-16 + mkdir -p /usr/local/bin && \ + printf "#!/usr/bin/env bash\nexec \"%s\" \"\$@\"\n" "$LLVM_CONFIG_PATH" > /usr/local/bin/llvm-config-16 && \ + chmod +x /usr/local/bin/llvm-config-16; \ + \ + # TVM Python bits need Cython + python3 -m pip install --no-cache-dir "cython>=0.29.36,<3.0"; \ + \ + # Clone + pin TileLang (bundled TVM), then build + git clone --recursive --branch "${TILELANG_BRANCH}" "${TILELANG_REPO}" /opt/tilelang && \ + cd /opt/tilelang && \ + git fetch --depth=1 origin "${TILELANG_COMMIT}" || true && \ + git checkout -f "${TILELANG_COMMIT}" && \ + git submodule update --init --recursive && \ + export CMAKE_ARGS="-DLLVM_CONFIG=${LLVM_CONFIG} ${CMAKE_ARGS:-}" && \ + bash ./install_rocm.sh' + +# ----------------------- +# Hadamard-transform (HIP build) +RUN /bin/bash -lc 'set -euo pipefail; \ + git clone --branch "${FHT_BRANCH}" "${FHT_REPO}" fast-hadamard-transform; \ + cd fast-hadamard-transform; \ + git checkout -f "${FHT_COMMIT}"; \ + python setup.py install' + +# ----------------------- +# Python tools +RUN python3 -m pip install --no-cache-dir \ + py-spy \ + pre-commit + +# ----------------------- # Performance environment variable. ENV HIP_FORCE_DEV_KERNARG=1 ENV HSA_NO_SCRATCH_RECLAIM=1