Skip to content
This repository has been archived by the owner on Oct 25, 2024. It is now read-only.

[NeuralChat] Support Neuralchat-vLLM serving with Docker #1187

Merged
merged 7 commits into from
Feb 5, 2024
Merged

Conversation

Spycsh
Copy link
Contributor

@Spycsh Spycsh commented Jan 24, 2024

Type of Change

feature
API not changed

Description

Support Neuralchat-vLLM serving with Docker

Expected Behavior & Potential Risk

Support Neuralchat-vLLM serving with Docker

How has this PR been tested?

on NV GPU

Dependency Change?

None

@Spycsh Spycsh requested a review from lvliang-intel as a code owner January 24, 2024 08:19
@hshen14
Copy link
Contributor

hshen14 commented Jan 26, 2024

Can we evaluate how to wrapper in a python API?

@Spycsh
Copy link
Contributor Author

Spycsh commented Jan 29, 2024

@hshen14 #1120 we already offer the Python API
by passing the PipelineConfig(serving_config=ServingConfig(...))

@hshen14 hshen14 merged commit 1988ddc into main Feb 5, 2024
12 checks passed
@hshen14 hshen14 deleted the vllm_docker branch February 5, 2024 05:41
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants