-
Notifications
You must be signed in to change notification settings - Fork 145
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
openvino support in vllm #65
openvino support in vllm #65
Conversation
* Adds Docker image and instructions for building it * Provides examples for starting the vLLM serving container with OpenAI API endpoint and interacting with it via bash shell * Includes additional server start-up parameters and a curl example for requesting completion with vLLM Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
for more information, see https://pre-commit.ci Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
@zahidulhaque please get all tests passed. Right now some typo issue was detected. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would add to the README motivation for using OpenVINO backend inference service, a few sentences like the runtime generates hardware target specific optimizations...
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
for more information, see https://pre-commit.ci
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Noted changes pertaining to License, hugging face token rename, service name change, and handling of results. Trusting your tests. Next time please strive for smaller PRs! Easier to digest all round.
comps/llms/text-generation/vllm-openvino/build_vllm_openvino.sh
Outdated
Show resolved
Hide resolved
comps/llms/text-generation/vllm-openvino/build_vllm_openvino.sh
Outdated
Show resolved
Hide resolved
Please contribute an e2e test for this microservice, like this one: https://github.com/opea-project/GenAIComps/blob/main/tests/test_reranks.sh, please name it as |
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com>
@chensuyue, i am working on writing the test case and will create a separate PR for this. |
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com> Signed-off-by: gadmarkovits <gad.markovits@intel.com>
Signed-off-by: Zahidul Haque <zahidul.haque@intel.com> Signed-off-by: sharanshirodkar7 <ssharanshirodkar7@gmail.com>
Description
This PR adds support for openvino as a backend inference engine to the vllm.
Type of change