Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
80cbe10c
Unverified
Commit
80cbe10c
authored
Aug 07, 2024
by
Ilya Lavrenov
Committed by
GitHub
Aug 07, 2024
Browse files
[OpenVINO] migrate to latest dependencies versions (#7251)
parent
b7645476
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
6 additions
and
33 deletions
+6
-33
Dockerfile.openvino
Dockerfile.openvino
+1
-1
docs/source/getting_started/openvino-installation.rst
docs/source/getting_started/openvino-installation.rst
+1
-1
requirements-openvino.txt
requirements-openvino.txt
+3
-30
setup.py
setup.py
+1
-1
No files found.
Dockerfile.openvino
View file @
80cbe10c
...
...
@@ -21,7 +21,7 @@ COPY setup.py /workspace/vllm/
# install build requirements
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/vllm/requirements-build.txt
# build vLLM with OpenVINO backend
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu
https://storage.openvinotoolkit.org/simple/wheels/pre-release
" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace/vllm/
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace/vllm/
COPY examples/ /workspace/vllm/examples
COPY benchmarks/ /workspace/vllm/benchmarks
...
...
docs/source/getting_started/openvino-installation.rst
View file @
80cbe10c
...
...
@@ -57,7 +57,7 @@ Install from source
.. code-block:: console
$ PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu
https://storage.openvinotoolkit.org/simple/wheels/pre-release
" VLLM_TARGET_DEVICE=openvino python -m pip install -v .
$ PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE=openvino python -m pip install -v .
.. _openvino_backend_performance_tips:
...
...
requirements-openvino.txt
View file @
80cbe10c
# Common dependencies
# -r requirements-common.txt
# TODO: remove temporary copy of all common dependencies once Optimum Intel will support Transformers >= 4.43.2
cmake >= 3.21
ninja # For faster builds.
psutil
sentencepiece # Required for LLaMA tokenizer.
numpy < 2.0.0
requests
tqdm
py-cpuinfo
transformers < 4.43
tokenizers >= 0.19.1 # Required for Llama 3.
fastapi
aiohttp
openai
uvicorn[standard]
pydantic >= 2.0 # Required for OpenAI server.
pillow # Required for image processing
prometheus_client >= 0.18.0
prometheus-fastapi-instrumentator >= 7.0.0
tiktoken >= 0.6.0 # Required for DBRX tokenizer
lm-format-enforcer == 0.10.3
outlines >= 0.0.43, < 0.1 # Requires torch >= 2.1.0
typing_extensions
filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4
pyzmq
gguf == 0.9.1
-r requirements-common.txt
# OpenVINO dependencies
torch >= 2.1.2
openvino ~= 2024.3.0.dev
openvino-tokenizers[transformers] ~= 2024.3.0.0.dev
optimum-intel[openvino] >= 1.18.1
openvino ~= 2024.3.0
optimum-intel[openvino] >= 1.18.2
setup.py
View file @
80cbe10c
...
...
@@ -272,7 +272,7 @@ def _build_custom_ops() -> bool:
def
_build_core_ext
()
->
bool
:
return
not
_is_neuron
()
and
not
_is_tpu
()
return
not
_is_neuron
()
and
not
_is_tpu
()
and
not
_is_openvino
()
def
get_hipcc_rocm_version
():
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment