mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-30 17:47:40 +02:00
Georgi Gerganov
491c4d7d2e
* ci : separate CUDA windows workflow + fix names * ci : rename workflow * ci : prefix cache names with workflow name * ci : rename build.yml -> build-cpu.yml * ci : cache keys * ci : fix windows cuda/hip concurrency of release workflow * ci : fix apple cache names * ci : add TODOs * cont : keep just the last cache * ci : update release concurrency to queue * ci : move the release trigger to ubuntu-slim * ci : hip add TODO * cont : improve words Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
83 lines
2.3 KiB
YAML
83 lines
2.3 KiB
YAML
name: HIP quality check
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/hip-quality-check.yml',
|
|
'**/*.cu',
|
|
'**/*.cuh',
|
|
'scripts/hip/gcn-cdna-vgpr-check.py'
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/hip-quality-check.yml',
|
|
'**/*.cu',
|
|
'**/*.cuh',
|
|
'scripts/hip/gcn-cdna-vgpr-check.py'
|
|
]
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
GGML_NLOOP: 3
|
|
GGML_N_THREADS: 1
|
|
LLAMA_ARG_LOG_COLORS: 1
|
|
LLAMA_ARG_LOG_PREFIX: 1
|
|
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
|
|
|
jobs:
|
|
ubuntu-22-hip-quality-check:
|
|
runs-on: ubuntu-22.04
|
|
container: rocm/dev-ubuntu-22.04:7.2.1
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Dependencies
|
|
id: depends
|
|
run: |
|
|
sudo apt-get update
|
|
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev python3
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: hip-quality-check-ubuntu-22.04
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Build with Werror
|
|
id: cmake_build
|
|
run: |
|
|
cmake -B build -S . \
|
|
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
|
|
-DGPU_TARGETS=gfx942 \
|
|
-DGGML_HIP=ON \
|
|
-DGGML_HIP_EXPORT_METRICS=Off \
|
|
-DCMAKE_HIP_FLAGS="-Werror -Wno-tautological-compare" \
|
|
-DCMAKE_BUILD_TYPE=Release
|
|
cd build
|
|
make -j $(nproc)
|
|
|
|
- name: Check for major VGPR spills
|
|
id: vgpr_check
|
|
run: |
|
|
cmake -B build -S . \
|
|
-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
|
|
-DGPU_TARGETS=gfx908 \
|
|
-DGGML_HIP=ON \
|
|
-DGGML_HIP_EXPORT_METRICS=On \
|
|
-DCMAKE_HIP_FLAGS="" \
|
|
-DCMAKE_BUILD_TYPE=Release
|
|
cd build
|
|
make -j $(nproc) 2>&1 | tee metrics.log | grep -v 'Rpass-analysis=kernel-resource-usage\|remark:\|^$'
|
|
python3 ../scripts/hip/gcn-cdna-vgpr-check.py metrics.log
|