hsliu
51d2570464
- Add comprehensive PRD, architecture design, and test design documents - Implement core modules: OmniLLM, AsyncOmniLLM, stage configurations - Add DiT scheduler and cache manager for diffusion models - Implement CLI integration with --omni flag support - Add API server and plugin system for vLLM integration - Create comprehensive test suite with fixtures - Update dependencies to vLLM 0.10.2 and PyTorch 2.8.0 - Add conda environment setup and package installation - Implement stage-based processing architecture - Add multimodal output processing capabilities This commit establishes the foundation for multi-modality models inference and serving with non-autoregressive structures.
21 lines
368 B
Python
21 lines
368 B
Python
"""
|
|
Configuration module for vLLM-omni.
|
|
"""
|
|
|
|
from .stage_config import (
|
|
OmniStageConfig,
|
|
DiTConfig,
|
|
DiTCacheConfig,
|
|
DiTCacheTensor,
|
|
create_ar_stage_config,
|
|
create_dit_stage_config,
|
|
)
|
|
|
|
__all__ = [
|
|
"OmniStageConfig",
|
|
"DiTConfig",
|
|
"DiTCacheConfig",
|
|
"DiTCacheTensor",
|
|
"create_ar_stage_config",
|
|
"create_dit_stage_config",
|
|
] |