Kevin H. Luu

[1/n][CI] Load models in CI from S3 instead of HF

5

1. Load some models from S3 path with `runai-model-streamer` instead of HF by default (only a few test jobs so far, listed below) 2. Add `runai-model-streamer` and `...-s3` into CI...

[ci] Consolidate Qwen models

6

Try to convert as many Qwen and Qwen2 to Qwen2.5 and reduce model size as we can.

[CI][Feature]: Add workflow to make sure PR branch is regularly synced with main

2

### 🚀 The feature, motivation and pitch To remind PR authors to sync with main, preventing out of sync PRs causing issues when merged into main. Ideally always synced within...

### 🚀 The feature, motivation and pitch Move commands like https://github.com/vllm-project/vllm/blob/main/.buildkite/test-pipeline.yaml#L809 to test image so it's easier to repro ### Alternatives _No response_ ### Additional context _No response_ ### Before...

[ci] Refactor CI files to use new CI pipeline generator

4

Change structure & format of CI files to use new vLLM project Buildkite pipeline generator https://github.com/vllm-project/ci-infra/tree/main/buildkite/pipeline_generator