Revert "[ROCm] remove triton-rocm commit pin and merge pins with triton.txt (#133438)"

This reverts commit f71c3d265a.

Reverted https://github.com/pytorch/pytorch/pull/133438 on behalf of https://github.com/jeanschmidt due to seems to have introduced breakages in linux binary builds ([comment](https://github.com/pytorch/pytorch/pull/133438#issuecomment-2308787310))

.ci/docker/centos-rocm/Dockerfile

@@ -108,10 +108,10 @@ ENV CMAKE_C_COMPILER cc
 ENV CMAKE_CXX_COMPILER c++
 COPY ./common/install_triton.sh install_triton.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ci_commit_pins/triton.txt triton.txt
+COPY ci_commit_pins/triton-rocm.txt triton-rocm.txt
 COPY triton_version.txt triton_version.txt
 RUN if [ -n "${TRITON}" ]; then bash ./install_triton.sh; fi
-RUN rm install_triton.sh common_utils.sh triton.txt triton_version.txt
+RUN rm install_triton.sh common_utils.sh triton-rocm.txt triton_version.txt
 
 # Install AOTriton (Early fail)
 COPY ./aotriton_version.txt aotriton_version.txt

.ci/docker/ci_commit_pins/triton-rocm.txt

@@ -0,0 +1 @@
+21eae954efa5bf584da70324b640288c3ee7aede

.ci/docker/ci_commit_pins/triton.txt

@@ -1 +1 @@
-55a4ab051c88ba2baa031e520a339d3fded6468f
+dedb7bdf339a3546896d4820366ca562c586bfa0

.ci/docker/common/install_triton.sh

@@ -12,7 +12,10 @@ conda_reinstall() {
   as_jenkins conda install -q -n py_$ANACONDA_PYTHON_VERSION -y --force-reinstall $*
 }
 
-if [ -n "${XPU_VERSION}" ]; then
+if [ -n "${ROCM_VERSION}" ]; then
+  TRITON_REPO="https://github.com/openai/triton"
+  TRITON_TEXT_FILE="triton-rocm"
+elif [ -n "${XPU_VERSION}" ]; then
   TRITON_REPO="https://github.com/intel/intel-xpu-backend-for-triton"
   TRITON_TEXT_FILE="triton-xpu"
 else

.ci/docker/ubuntu-rocm/Dockerfile

@@ -100,10 +100,10 @@ ARG TRITON
 # try to reach out to S3, which docker build runners don't have access
 COPY ./common/install_triton.sh install_triton.sh
 COPY ./common/common_utils.sh common_utils.sh
-COPY ci_commit_pins/triton.txt triton.txt
+COPY ci_commit_pins/triton-rocm.txt triton-rocm.txt
 COPY triton_version.txt triton_version.txt
 RUN if [ -n "${TRITON}" ]; then bash ./install_triton.sh; fi
-RUN rm install_triton.sh common_utils.sh triton.txt triton_version.txt
+RUN rm install_triton.sh common_utils.sh triton-rocm.txt triton_version.txt
 
 # Install AOTriton
 COPY ./aotriton_version.txt aotriton_version.txt

.circleci/scripts/binary_populate_env.sh

@@ -90,7 +90,7 @@ fi
 if [[ "$PACKAGE_TYPE" =~ .*wheel.* && -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*rocm.* && $(uname) == "Linux" ]]; then
     TRITON_REQUIREMENT="pytorch-triton-rocm==${TRITON_VERSION}; ${TRITON_CONSTRAINT}"
     if [[ -n "$PYTORCH_BUILD_VERSION" && "$PYTORCH_BUILD_VERSION" =~ .*dev.* ]]; then
-        TRITON_SHORTHASH=$(cut -c1-10 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton.txt)
+        TRITON_SHORTHASH=$(cut -c1-10 $PYTORCH_ROOT/.ci/docker/ci_commit_pins/triton-rocm.txt)
         TRITON_REQUIREMENT="pytorch-triton-rocm==${TRITON_VERSION}+${TRITON_SHORTHASH}; ${TRITON_CONSTRAINT}"
     fi
     if [[ -z "${PYTORCH_EXTRA_INSTALL_REQUIREMENTS:-}" ]]; then

.github/scripts/build_triton_wheel.py

@@ -15,7 +15,9 @@ REPO_DIR = SCRIPT_DIR.parent.parent
 
 def read_triton_pin(device: str = "cuda") -> str:
     triton_file = "triton.txt"
-    if device == "xpu":
+    if device == "rocm":
+        triton_file = "triton-rocm.txt"
+    elif device == "xpu":
         triton_file = "triton-xpu.txt"
     with open(REPO_DIR / ".ci" / "docker" / "ci_commit_pins" / triton_file) as f:
         return f.read().strip()

.github/workflows/build-triton-wheel.yml

@@ -13,6 +13,7 @@ on:
       - .github/scripts/build_triton_wheel.py
       - .github/ci_commit_pins/triton.txt
       - .ci/docker/ci_commit_pins/triton.txt
+      - .ci/docker/ci_commit_pins/triton-rocm.txt
       - .ci/docker/ci_commit_pins/triton-xpu.txt
   pull_request:
     paths:
@@ -20,6 +21,7 @@ on:
       - .github/scripts/build_triton_wheel.py
       - .github/ci_commit_pins/triton.txt
       - .ci/docker/ci_commit_pins/triton.txt
+      - .ci/docker/ci_commit_pins/triton-rocm.txt
       - .ci/docker/ci_commit_pins/triton-xpu.txt
 
 concurrency:

CODEOWNERS

@@ -57,6 +57,7 @@ nn/qat/ @jerryzh168
 # Docker
 /.ci/docker/ @jeffdaily
 /.ci/docker/ci_commit_pins/triton.txt @desertfire @Chillee @eellison @shunting314 @bertmaher @jeffdaily @jataylo @jithunnair-amd @pruthvistony
+/.ci/docker/ci_commit_pins/triton-rocm.txt @jeffdaily @jataylo @jithunnair-amd @pruthvistony
 /.ci/docker/ci_commit_pins/triton-xpu.txt @EikanWang @gujinghui
 
 # Github Actions