Skip to content

Conversation

pinglin
Copy link
Member

@pinglin pinglin commented Apr 7, 2025

Because

  • ARM64 platform support is needed for broader hardware compatibility
  • Model configuration validation needed improvement for better reliability
  • Project installation process required more flexibility, especially for development workflows
  • The deprecated init-templates Dockerfile needed replacement
  • Error handling needed enhancement for better user experience

This commit

  • Adds functions to check required fields in model configurations
  • Implements build environment preparation functionality
  • Adds support for ARM64-specific package processing
  • Creates Docker image build configurations for different architectures
  • Introduces command-line arguments for editable project installations
  • Improves error handling throughout the CLI tool
  • Creates separate Dockerfiles for standard and ARM architectures
  • Updates input validation for chat and completion tasks in ray_io module

This commit introduces several enhancements to the CLI tool, including:

- Added functions for checking required fields in model configurations and preparing build environments.
- Implemented support for processing ARM64-specific packages and building Docker images with appropriate configurations.
- Introduced new command-line arguments for editable project installations and improved error handling.
- Created Dockerfiles for standard and ARM architectures, replacing the deprecated init-templates Dockerfile.

Additionally, the commit updates the input validation for chat and completion tasks in the ray_io module, ensuring required fields are checked and defaults are overridden as necessary.
@pinglin pinglin force-pushed the pinglin/add-vllm-arm64 branch from 09c4d68 to 1c2f042 Compare April 8, 2025 04:56
@pinglin pinglin merged commit 8fa8fed into main Apr 10, 2025
7 checks passed
@pinglin pinglin deleted the pinglin/add-vllm-arm64 branch April 10, 2025 20:30
pinglin pushed a commit that referenced this pull request Apr 18, 2025
🤖 I have created a release *beep* *boop*
---


##
[0.17.0](v0.16.2...v0.17.0)
(2025-04-15)


### Features

* **cli:** enhance CLI functionality and add Docker support
([#268](#268))
([8fa8fed](8fa8fed))
* **ray:** add high scale config
([#261](#261))
([ccf24b2](ccf24b2))


### Bug Fixes

* **client, const:** add secure argument to latest SDK client
([#271](#271))
([1355086](1355086))
* **ray:** align autoscale config
([#263](#263))
([c07b787](c07b787))
* **ray:** fix config not applied
([0bc15de](0bc15de))
* **ray:** override max replica
([7e456ca](7e456ca))
* **ray:** update high scale model config
([#264](#264))
([1086e6d](1086e6d))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
No open projects
Status: No status
Development

Successfully merging this pull request may close these issues.

2 participants