Skip to content

LLM inference in C/C++

C++ ggml

ci : enable hf-jobs on server-cuda (#28258)

Sigbjørn Skjæretd5fec32a87e8
diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.yml
index 675ddbaaa5..d9ad2fcd0d 100644
--- a/.github/workflows/server-self-hosted.yml
+++ b/.github/workflows/server-self-hosted.yml
@@ -102,7 +102,7 @@ jobs:
./tests.sh
server-cuda:
- runs-on: [self-hosted, llama-server, Linux, NVIDIA]
+ runs-on: "hf-jobs-t4-small:cuda13"
steps:
- name: Clone
@@ -112,12 +112,42 @@ jobs:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
+ - name: Install dependencies
+ run: |
+ sudo apt update
+ sudo apt install -y cmake libssl-dev python3 python3-venv python3-pip
+
+ - name: ccache
+ uses: ggml-org/[email protected]
+ with:
+ restore: false
+ save: false
+
+ - name: ccache-buckets-restore
+ uses: ./.github/actions/ccache-buckets
+ with:
+ key: self-hosted-server-cuda
+ folder: llama.cpp
+ hf_bucket: ggml-org/cache
+
- name: Build
id: cmake_build
run: |
- cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON
+ cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc
cmake --build build --config Release -j $(nproc) --target llama-server
+ - name: ccache-buckets-save
+ if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+ uses: ./.github/actions/ccache-buckets
+ env:
+ HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
+ with:
+ key: self-hosted-server-cuda
+ folder: llama.cpp
+ evict-old-files: 1d
+ hf_bucket: ggml-org/cache
+ save: true
+
- name: Python setup
id: setup_python
run: |