2025-09-11 14:32:51 +08:00
|
|
|
|
# vLLM-omni Examples
|
|
|
|
|
|
|
2025-09-28 21:58:48 +08:00
|
|
|
|
A curated set of runnable samples demonstrating vLLM-omni usage.
|
2025-09-11 14:32:51 +08:00
|
|
|
|
|
2025-09-28 21:58:48 +08:00
|
|
|
|
## Directory Overview
|
2025-09-11 14:32:51 +08:00
|
|
|
|
|
2025-09-28 21:58:48 +08:00
|
|
|
|
- **basic/** – Quick-start scripts for text-only flows.
|
|
|
|
|
|
- `text_generation.py` – Minimal CPU-friendly text generation with vLLM.
|
|
|
|
|
|
- `api_client.py` – Calls the FastAPI server using the JSON API.
|
|
|
|
|
|
- `docker_run.py` – Template for launching the server in Docker.
|
|
|
|
|
|
- **omni/** – Multi-stage AR → DiT pipelines powered by diffusers.
|
|
|
|
|
|
- `ar_dit_diffusers.py` – Runs Qwen3 (AR) feeding Stable Diffusion 2.1 (DiT).
|
|
|
|
|
|
- `configs/ar_dit_local.yaml` – Sample plugin config referencing local weights.
|
|
|
|
|
|
- **advanced/** – Placeholder for upcoming complex flows (Ray, benchmarking).
|
2025-09-11 14:32:51 +08:00
|
|
|
|
|
2025-09-28 21:58:48 +08:00
|
|
|
|
See the subdirectory READMEs for usage instructions.
|
