TeleFuser¶
A high-performance runtime for world model inference and multimodal generation, built for long-running pipelines, distributed execution, and production service interfaces.
PyTorch 2.6+ CUDA 12.8+ Triton kernels FastAPI service Ray distributed
Runtime Capabilities¶
World Model Runtime
Continuous execution, stateful sessions, and bidirectional control loops.
Parallel Inference
Ulysses, Ring Attention, tensor parallelism, pipeline parallelism, and FSDP.
Optimized Operators
Compile-aware ops with eager CUDA Triton kernels and PyTorch native fallbacks.
Streaming Service
FastAPI batch serving and LiveKit-backed rooms for server-push and resilient interactive WebRTC.
Feature Cache
AdaTaylorCache and runtime cache controls for repeated generation workloads.
Extensible Pipelines
Reusable stages, model configs, schedulers, and pipeline orchestration.
Supported Models¶
World Model and Real-Time¶
| Model | Tasks | Description |
|---|---|---|
| LingBot-World v2 | Bidirectional streaming | Camera-controlled interactive world model via LiveKit |
| LingBot-World-Fast | Bidirectional streaming | Legacy/causal-fast model via LiveKit reliable data messages |
Video Generation¶
| Model | Tasks | Description |
|---|---|---|
| WanVideo (Wan2.1 / Wan2.2) | T2V, I2V, FL2V | Video generation and editing |
| HunyuanVideo | T2V, I2V | Video generation |
| LTX Video | I2V + Audio | Video generation with audio |
| FlashVSR | VSR | Video super-resolution |
| LiveAct | S2V | Speech-to-video |
| LongCat-Video | T2V, I2V | Long video generation |
| LingBot-Video | T2I, T2V, TI2V, MoE refiner | Precision-first Dense and MoE video generation |
Image Generation¶
| Model | Tasks | Description |
|---|---|---|
| Qwen-Image | T2I, Edit | Image generation and editing |
| Z-Image | T2I | Image generation |
| Flux2 Klein | T2I | Image generation |
Quick Start¶
# Install
pip install telefuser
# Batch serving
telefuser serve /path/to/pipeline.py --port 8000
# LiveKit-backed streaming (Python SDK included in the base install)
telefuser stream-serve examples/lingbot/lingbot_world_fast_image_to_video_h100.py \
--livekit-url ws://127.0.0.1:7880 \
--livekit-api-key devkey --livekit-api-secret secret \
-p 8088