diff --git a/.github/workflows/buildAndTest.yml b/.github/workflows/buildAndTest.yml
index c6d345860..08ab86571 100644
--- a/.github/workflows/buildAndTest.yml
+++ b/.github/workflows/buildAndTest.yml
@@ -2,11 +2,11 @@
 name: Build and Test
 
 on:
-  pull_request:
-    branches: [main]
-  push:
-    branches: [main]
-  workflow_dispatch:
+  # pull_request:
+  #   branches: [main]
+  # push:
+  #   branches: [main]
+  # workflow_dispatch:
 
 # Ensure that only a single job or workflow using the same
 # concurrency group will run at a time. This would cancel
@@ -30,7 +30,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        os-arch: [ubuntu-x86_64, macos-arm64, windows-x86_64]
+        os-arch: [macos-arm64, windows-x86_64]
         llvm-build: [in-tree, out-of-tree]
         torch-binary: [ON]
         torch-version: [nightly, stable]
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 000000000..4bb27526b
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,77 @@
+name: CI
+
+on:
+  workflow_dispatch:
+  workflow_call:
+  pull_request:
+    branches: [main]
+  push:
+    branches: [main]
+
+concurrency:
+  # A PR number if a pull request and otherwise the commit hash. This cancels
+  # queued and in-progress runs for the same PR (presubmit) or commit
+  # (postsubmit).
+  group: ci-build-test-cpp-linux-${{ github.event.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  build-test-linux:
+    strategy:
+      fail-fast: true
+      matrix:
+        torch-version: [nightly, stable]
+    name: Build and Test (Linux, torch-${{ matrix.torch-version }}, assertions)
+    runs-on: torch-mlir-cpubuilder-manylinux-x86-64
+    env:
+      CACHE_DIR: ${{ github.workspace }}/.container-cache
+    steps:
+      - name: Configure local git mirrors
+        run: |
+          # Our stock runners have access to certain local git caches. If these
+          # files are available, it will prime the cache and configure git to
+          # use them. Practically, this eliminates network/latency for cloning
+          # llvm.
+          if [[ -x /gitmirror/scripts/trigger_update_mirrors.sh ]]; then
+            /gitmirror/scripts/trigger_update_mirrors.sh
+            /gitmirror/scripts/git_config.sh
+          fi
+      - name: "Checking out repository"
+        uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0
+        with:
+          submodules: true
+
+      - name: Enable cache
+        uses: actions/cache/restore@v3
+        with:
+          path: ${{ env.CACHE_DIR }}
+          key: build-test-cpp-asserts-manylinux-v2-${{ github.sha }}
+          restore-keys: |
+            build-test-cpp-asserts-manylinux-v2-
+
+      - name: Install python deps (torch-${{ matrix.torch-version }})
+        run: |
+          export cache_dir="${{ env.CACHE_DIR }}"
+          bash build_tools/ci/install_python_deps.sh ${{ matrix.torch-version }}
+
+      - name: Build project
+        run: |
+          export cache_dir="${{ env.CACHE_DIR }}"
+          bash build_tools/ci/build_posix.sh
+
+      - name: Save cache
+        uses: actions/cache/save@v3
+        if: ${{ !cancelled() }}
+        with:
+          path: ${{ env.CACHE_DIR }}
+          key: build-test-cpp-asserts-manylinux-v2-${{ github.sha }}
+
+      - name: Test project (torch-${{ matrix.torch-version }})
+        run: |
+          export cache_dir="${{ env.CACHE_DIR }}"
+          bash build_tools/ci/test_posix.sh ${{ matrix.torch-version }}
+
+      - name: Check generated sources (torch-nightly only)
+        if: ${{ matrix.torch-version == 'nightly' }}
+        run: |
+          bash build_tools/ci/check_generated_sources.sh
diff --git a/.github/workflows/releaseSnapshotPackage.yml b/.github/workflows/releaseSnapshotPackage.yml
index 71acd9ac3..8a0ec9144 100644
--- a/.github/workflows/releaseSnapshotPackage.yml
+++ b/.github/workflows/releaseSnapshotPackage.yml
@@ -2,9 +2,8 @@
 name: Release snapshot package
 
 on:
-  schedule:
-    - cron: '0 11 * * *'
-
+  # schedule:
+  #   - cron: '0 11 * * *'
   workflow_dispatch:
 
 jobs:
diff --git a/build_tools/ci/build_posix.sh b/build_tools/ci/build_posix.sh
new file mode 100755
index 000000000..c6e7e168d
--- /dev/null
+++ b/build_tools/ci/build_posix.sh
@@ -0,0 +1,60 @@
+#!/bin/bash
+
+set -eu -o errtrace
+
+this_dir="$(cd $(dirname $0) && pwd)"
+repo_root="$(cd $this_dir/../.. && pwd)"
+build_dir="$repo_root/build"
+install_dir="$repo_root/install"
+mkdir -p "$build_dir"
+build_dir="$(cd $build_dir && pwd)"
+cache_dir="${cache_dir:-}"
+
+# Setup cache dir.
+if [ -z "${cache_dir}" ]; then
+  cache_dir="${repo_root}/.build-cache"
+  mkdir -p "${cache_dir}"
+  cache_dir="$(cd ${cache_dir} && pwd)"
+fi
+echo "Caching to ${cache_dir}"
+mkdir -p "${cache_dir}/ccache"
+mkdir -p "${cache_dir}/pip"
+
+python="$(which python)"
+echo "Using python: $python"
+
+export CMAKE_TOOLCHAIN_FILE="$this_dir/linux_default_toolchain.cmake"
+export CC=clang
+export CXX=clang++
+export CCACHE_DIR="${cache_dir}/ccache"
+export CCACHE_MAXSIZE="350M"
+export CMAKE_C_COMPILER_LAUNCHER=ccache
+export CMAKE_CXX_COMPILER_LAUNCHER=ccache
+
+# Clear ccache stats.
+ccache -z
+
+cd $repo_root
+
+echo "::group::CMake configure"
+cmake -S "$repo_root/externals/llvm-project/llvm" -B "$build_dir" \
+  -GNinja \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DPython3_EXECUTABLE="$(which python)" \
+  -DLLVM_ENABLE_ASSERTIONS=ON \
+  -DCMAKE_INSTALL_PREFIX="$install_dir" \
+  -DCMAKE_INSTALL_LIBDIR=lib \
+  -DLLVM_ENABLE_PROJECTS=mlir \
+  -DLLVM_EXTERNAL_PROJECTS="torch-mlir" \
+  -DLLVM_EXTERNAL_TORCH_MLIR_SOURCE_DIR="$repo_root" \
+  -DLLVM_TARGETS_TO_BUILD=host \
+  -DMLIR_ENABLE_BINDINGS_PYTHON=ON \
+  -DTORCH_MLIR_ENABLE_LTC=ON
+echo "::endgroup::"
+
+echo "::group::Build"
+cmake --build "$build_dir" --target tools/torch-mlir/all -- -k 0
+echo "::endgroup::"
+
+# Show ccache stats.
+ccache --show-stats
diff --git a/build_tools/ci/check_generated_sources.sh b/build_tools/ci/check_generated_sources.sh
new file mode 100755
index 000000000..719e221d7
--- /dev/null
+++ b/build_tools/ci/check_generated_sources.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+
+set -eu -o errtrace
+
+this_dir="$(cd $(dirname $0) && pwd)"
+repo_root="$(cd $this_dir/../.. && pwd)"
+
+function _check_file_not_changed_by() {
+  # _check_file_not_changed_by <cmd> <file>
+  cmd="$1"
+  file="$2"
+  file_backup="$PWD/$(basename $file)"
+  file_new="$PWD/$(basename $file).new"
+  # Save the original file.
+  cp "$file" "$file_backup"
+  # Run the command to regenerate it.
+  "$1" || return 1
+  # Save the new generated file.
+  cp "$file" "$file_new"
+  # Restore the original file. We want this function to not change the user's
+  # working tree state.
+  mv "$file_backup" "$file"
+  # We use git-diff as "just a diff program" (no SCM stuff) because it has
+  # nicer output than regular `diff`.
+  if ! git diff --no-index --quiet "$file" "$file_new"; then
+    echo "#######################################################"
+    echo "Generated file '${file}' is not up to date (see diff below)"
+    echo ">>> Please run '${cmd}' to update it <<<"
+    echo "#######################################################"
+    git diff --no-index --color=always "$file" "$file_new"
+    # TODO: Is there a better cleanup strategy that doesn't require duplicating
+    # this inside and outside the `if`?
+    rm "$file_new"
+    return 1
+  fi
+  rm "$file_new"
+}
+
+echo "::group:: Check that update_abstract_interp_lib.sh has been run"
+_check_file_not_changed_by $repo_root/build_tools/update_abstract_interp_lib.sh $repo_root/lib/Dialect/Torch/Transforms/AbstractInterpLibrary.cpp
+echo "::endgroup::"
+
+echo "::group:: Check that update_torch_ods.sh has been run"
+_check_file_not_changed_by $repo_root/build_tools/update_torch_ods.sh $repo_root/include/torch-mlir/Dialect/Torch/IR/GeneratedTorchOps.td
+echo "::endgroup::"
diff --git a/build_tools/ci/install_python_deps.sh b/build_tools/ci/install_python_deps.sh
new file mode 100755
index 000000000..6b49689ce
--- /dev/null
+++ b/build_tools/ci/install_python_deps.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+
+set -eu -o errtrace
+
+this_dir="$(cd $(dirname $0) && pwd)"
+repo_root="$(cd $this_dir/../.. && pwd)"
+torch_version="${1:-unknown}"
+
+echo "::group::installing llvm python deps"
+python -m pip install --no-cache-dir -r $repo_root/externals/llvm-project/mlir/python/requirements.txt
+echo "::endgroup::"
+
+case $torch_version in
+  nightly)
+    echo "::group::installing nightly torch"
+    python3 -m pip install --no-cache-dir -r $repo_root/requirements.txt
+    python3 -m pip install --no-cache-dir -r $repo_root/torchvision-requirements.txt
+    echo "::endgroup::"
+    ;;
+  stable)
+    echo "::group::installing stable torch"
+    python3 -m pip install --no-cache-dir torch torchvision --index-url https://download.pytorch.org/whl/cpu
+    python3 -m pip install --no-cache-dir -r $repo_root/build-requirements.txt
+    echo "::endgroup::"
+    ;;
+  *)
+    echo "Unrecognized torch version '$torch_version' (specify 'nightly' or 'stable' with cl arg)"
+    exit 1
+    ;;
+esac
+
+echo "::group::installing test requirements"
+python -m pip install --no-cache-dir -r $repo_root/test-requirements.txt
+echo "::endgroup::"
diff --git a/build_tools/ci/linux_default_toolchain.cmake b/build_tools/ci/linux_default_toolchain.cmake
new file mode 100644
index 000000000..4e0c36c71
--- /dev/null
+++ b/build_tools/ci/linux_default_toolchain.cmake
@@ -0,0 +1,14 @@
+message(STATUS "Enabling thin archives (static libraries will not be relocatable)")
+set(CMAKE_C_ARCHIVE_APPEND "<CMAKE_AR> qT <TARGET> <LINK_FLAGS> <OBJECTS>")
+set(CMAKE_CXX_ARCHIVE_APPEND "<CMAKE_AR> qT <TARGET> <LINK_FLAGS> <OBJECTS>")
+set(CMAKE_C_ARCHIVE_CREATE "<CMAKE_AR> crT <TARGET> <LINK_FLAGS> <OBJECTS>")
+set(CMAKE_CXX_ARCHIVE_CREATE "<CMAKE_AR> crT <TARGET> <LINK_FLAGS> <OBJECTS>")
+
+set(CMAKE_EXE_LINKER_FLAGS_INIT "-fuse-ld=lld -Wl,--gdb-index")
+set(CMAKE_MODULE_LINKER_FLAGS_INIT "-fuse-ld=lld -Wl,--gdb-index")
+set(CMAKE_SHARED_LINKER_FLAGS_INIT "-fuse-ld=lld -Wl,--gdb-index")
+
+set(CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -gsplit-dwarf -ggnu-pubnames")
+set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -gsplit-dwarf -ggnu-pubnames")
+set(CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -gsplit-dwarf -ggnu-pubnames")
+set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -gsplit-dwarf -ggnu-pubnames")
diff --git a/build_tools/ci/test_posix.sh b/build_tools/ci/test_posix.sh
new file mode 100755
index 000000000..8cc68d77b
--- /dev/null
+++ b/build_tools/ci/test_posix.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+
+set -eu -o errtrace
+
+this_dir="$(cd $(dirname $0) && pwd)"
+repo_root="$(cd $this_dir/../.. && pwd)"
+torch_version="${1:-unknown}"
+
+export PYTHONPATH="$repo_root/build/tools/torch-mlir/python_packages/torch_mlir:$repo_root/projects/pt1"
+
+echo "::group::Run Linalg e2e integration tests"
+python -m e2e_testing.main --config=linalg -v
+echo "::endgroup::"
+
+echo "::group::Run make_fx + TOSA e2e integration tests"
+python -m e2e_testing.main --config=make_fx_tosa -v
+echo "::endgroup::"
+
+echo "::group::Run TOSA e2e integration tests"
+python -m e2e_testing.main --config=tosa -v
+echo "::endgroup::"
+
+case $torch_version in
+  nightly)
+    # Failing with: NotImplementedError: 
+    #   Could not run 'aten::empty.memory_format' with arguments from the 'Lazy' backend.
+    # As of 2024-01-07
+    # echo "::group::Run Lazy Tensor Core e2e integration tests"
+    # python -m e2e_testing.main --config=lazy_tensor_core -v
+    # echo "::endgroup::"
+
+    # TODO: There is one failing test in this group on stable. It could
+    # be xfailed vs excluding entirely.
+    echo "::group::Run TorchDynamo e2e integration tests"
+    python -m e2e_testing.main --config=torchdynamo -v
+    echo "::endgroup::"
+    ;;
+  stable)
+    ;;
+  *)
+    echo "Unrecognized torch version '$torch_version' (specify 'nightly' or 'stable' with cl arg)"
+    exit 1
+    ;;
+esac
diff --git a/projects/pt1/python/torch_mlir_e2e_test/framework.py b/projects/pt1/python/torch_mlir_e2e_test/framework.py
index f1fbad2ec..388976256 100644
--- a/projects/pt1/python/torch_mlir_e2e_test/framework.py
+++ b/projects/pt1/python/torch_mlir_e2e_test/framework.py
@@ -24,11 +24,19 @@ import abc
 from typing import Any, Callable, List, NamedTuple, Optional, TypeVar, Union, Dict
 from itertools import repeat
 
+import os
 import sys
 import traceback
 
-import torch
 import multiprocess as mp
+from multiprocess import set_start_method
+try:
+    set_start_method("spawn")
+except RuntimeError:
+    # Children can error here so we suppress.
+    pass
+
+import torch
 
 TorchScriptValue = Union[int, float, List['TorchScriptValue'],
                          Dict['TorchScriptValue',
@@ -316,8 +324,16 @@ def compile_and_run_test(test: Test, config: TestConfig, verbose=False) -> Any:
 
 
 def run_tests(tests: List[Test], config: TestConfig, sequential=False, verbose=False) -> List[TestResult]:
-    """Invoke the given `Test`'s with the provided `TestConfig`."""
-    num_processes = min(int(mp.cpu_count() * 1.1), len(tests))
+    """Invoke the given `Test`'s with the provided `TestConfig`.""" 
+    num_processes = min(int(mp.cpu_count() * 0.8) + 1, len(tests))
+    try:
+        env_concurrency = int(os.getenv("TORCH_MLIR_TEST_CONCURRENCY", "0"))
+    except ValueError as e:
+        raise ValueError("Bad value for TORCH_MLIR_TEST_CONCURRENCY env var: "
+                         "Expected integer.") from e
+    if env_concurrency > 0:
+        num_processes = min(num_processes, env_concurrency)
+
     # TODO: We've noticed that on certain 2 core machine parallelizing the tests
     # makes the llvm backend legacy pass manager 20x slower than using a
     # single process. Need to investigate the root cause eventually. This is a
@@ -344,7 +360,7 @@ def run_tests(tests: List[Test], config: TestConfig, sequential=False, verbose=F
     pool = mp.Pool(num_processes)
     arg_list = zip(tests, repeat(config))
     handles = pool.starmap_async(compile_and_run_test, arg_list)
-    results = handles.get()
+    results = handles.get(timeout=360)
 
     tests_with_results = {result.unique_name for result in results}
     all_tests = {test.unique_name for test in tests}
diff --git a/python/CMakeLists.txt b/python/CMakeLists.txt
index b8f839445..d725aae6c 100644
--- a/python/CMakeLists.txt
+++ b/python/CMakeLists.txt
@@ -46,6 +46,13 @@ declare_mlir_python_sources(TorchMLIRPythonSources.Tools
     tools/import_onnx/__main__.py
 )
 
+declare_mlir_python_sources(TorchMLIRSiteInitialize
+  ROOT_DIR "${TORCH_MLIR_PYTHON_ROOT_DIR}"
+  ADD_TO_PARENT TorchMLIRPythonSources
+  SOURCES
+    _mlir_libs/_site_initialize_0.py
+)
+
 ################################################################################
 # Extensions
 ################################################################################
@@ -79,6 +86,7 @@ set(_source_components
   MLIRPythonExtension.RegisterEverything
   TorchMLIRPythonSources
   TorchMLIRPythonExtensions
+  TorchMLIRSiteInitialize
 
   # Sources related to optional Torch extension dependent features. Typically
   # empty unless if project features are enabled.
diff --git a/python/torch_mlir/_mlir_libs/_site_initialize_0.py b/python/torch_mlir/_mlir_libs/_site_initialize_0.py
new file mode 100644
index 000000000..3b93b1fa9
--- /dev/null
+++ b/python/torch_mlir/_mlir_libs/_site_initialize_0.py
@@ -0,0 +1,9 @@
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+# Also available under a BSD-style license. See LICENSE.
+
+# Multi-threading rarely helps the frontend and we are also running in contexts
+# where we want to run a lot of test parallelism (and nproc*nproc threads
+# puts a large load on the system and virtual memory).
+disable_multithreading = True