tzhouam 4609afa613 Refactor sampled_token_ids assignment in OmniGPUModelRunner ...

- Simplified the assignment of sampled_token_ids by removing the conditional check for "model_stage".
- Ensured consistent handling of sampled_token_ids for improved clarity and maintainability.

2025-10-22 17:42:29 +08:00

..

__init__.py

Initial vLLM-omni repository structure

2025-09-11 14:32:51 +08:00

gpu_diffusion_model_runner.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

gpu_diffusion_worker.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

gpu_model_runner.py

Refactor sampled_token_ids assignment in OmniGPUModelRunner

2025-10-22 17:42:29 +08:00

model_runner.py

Add OmniGPUModelRunner and OmniModelInputForGPU classes

2025-10-22 15:33:11 +08:00