A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 18:15 UTC
[Misc] Update dockerfile for CPU to cover protobuf installation (#7182)
PHILO-HE committed
Aug 16, 2024 at 01:03 UTC
f4da5f7b6d296aabd00c2ed068cab4d3605ff80e
3 files changed
+3
-2
.buildkite/run-cpu-test.sh
+1
-1
@@ -22,7 +22,7 @@ docker exec cpu-test-avx2 bash -c "python3 examples/offline_inference.py"
22
23
# Run basic model test
24
docker exec cpu-test bash -c "
25
- pip install pytest Pillow protobuf
25
+ pip install pytest
26
pytest -v -s tests/models -m \"not vlm\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_oot_registration.py --ignore=tests/models/test_registry.py --ignore=tests/models/test_jamba.py --ignore=tests/models/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
27
28
# online inference
Dockerfile.cpu
+1
-1
@@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt \
13
RUN --mount=type=cache,target=/root/.cache/pip \
14
pip install intel-openmp
15
16
-ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so:$LD_PRELOAD"
16
+ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so"
17
18
RUN echo 'ulimit -c 0' >> ~/.bashrc
19
requirements-common.txt
+1
@@ -6,6 +6,7 @@ tqdm
6
py-cpuinfo
7
transformers >= 4.43.2 # Required for Chameleon and Llama 3.1 hotfox.
8
tokenizers >= 0.19.1 # Required for Llama 3.
9
+protobuf # Required by LlamaTokenizer.
10
fastapi
11
aiohttp
12
openai