forked from nod-ai/shark-ai
-
Notifications
You must be signed in to change notification settings - Fork 0
98 lines (83 loc) · 3.72 KB
/
ci-shark-platform2.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
# Copyright 2024 Advanced Micro Devices, Inc.
#
# Licensed 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
name: CI - fast from source shark-platform
on:
workflow_dispatch:
pull_request:
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). The workflow name is prepended to avoid conflicts between
# different workflows.
group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
cancel-in-progress: true
jobs:
test_shortfin_llm_server:
name: "Integration Tests - Shortfin LLM Server"
strategy:
matrix:
version: [3.11]
fail-fast: false
runs-on: nodai-amdgpu-mi250-x86-64
defaults:
run:
shell: bash
env:
PIP_CACHE_DIR: "${{ github.workspace }}/.pip-cache"
steps:
- name: "Setting up Python"
id: setup_python
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{matrix.version}}
- name: "Checkout Code"
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Cache Pip Packages
uses: actions/cache@6849a6489940f00c2f30c0fb92c6274307ccb58a # v4.1.2
id: cache-pip
with:
path: ${{ env.PIP_CACHE_DIR }}
key: pip-${{ steps.setup_python.outputs.python-version }}-${{ hashFiles('*requirements.txt') }}
- name: Install pip deps
run: |
python -m pip install --no-compile --upgrade pip
# Note: We install in three steps in order to satisfy requirements
# from non default locations first. Installing the PyTorch CPU
# wheels saves multiple minutes and a lot of bandwidth on runner setup.
pip install --no-compile -r pytorch-cpu-requirements.txt
pip install --no-compile -r requirements.txt -e sharktank/
# Install latest iree-tubrine.
pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \
-e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
# Try with the latest IREE nightly releases, not what iree-turbine pins.
# We could also pin to a known working or stable version.
# This should eventually stabilize. Do the best we can for now.
pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \
iree-base-compiler \
iree-base-runtime
- name: Clone IREE with matching version
run: |
# Get IREE version
IREE_VERSION=$(pip show iree-base-compiler | grep Version: | cut -d' ' -f2)
echo "Required IREE version: ${IREE_VERSION}"
EXPECTED_TAG="iree-${IREE_VERSION}"
# Clone or update IREE repository
IREE_PATH="../iree"
if [ -d "$IREE_PATH" ] && [ "$(cd $IREE_PATH && git describe --tags --exact-match 2>/dev/null)" = "$EXPECTED_TAG" ]; then
echo "IREE repository already at correct version"
else
rm -rf "$IREE_PATH"
git clone --depth 1 --branch "$EXPECTED_TAG" --recurse-submodules --shallow-submodules https://github.com/iree-org/iree.git "$IREE_PATH"
fi
- name: Install CMake
uses: ssrobins/install-cmake@v1 # this action installs cmake into the action workspace
- name: Install shortfin via dev_me.py
run: cd shortfin && python dev_me.py
- name: Run LLM Integration Tests
run: pytest -v build_tools/integration_tests/llm --log-cli-level=INFO