Skip to content

TeleFuser

An open-source streaming inference and serving framework for real-time world models and multimodal generation, built for continuous pipelines, distributed GPU 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
ABot-World-0-5B-LF Single-GPU interactive generation Direct HTTP or LiveKit browser control with persistent causal KV state

Video Generation

Model Tasks Description
WanVideo (Wan2.1 / Wan2.2) T2V, I2V, FL2V Video generation and editing
LTX Video I2V + Audio Video generation with audio
LTX-2.5 Distilled T2V, I2V + Audio ModuleManager-backed six-stage pipeline with ½/4-H100 Ulysses SP
MiniMax H3 T2VA, FL2VA, Ref2VA + Audio Local 768p joint audio-video generation
FlashVSR VSR Video super-resolution
SwiftVR Causal video restoration Stateful restoration with BF16, compile, FP8Linear, Ulysses SP, and stage-parallel options
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

Vision-Language-Action

Model Tasks Description
LingBot-VLA v2 Robot manipulation Vision-language-action inference for supported robot profiles

Start Here

Documentation Sections


Switch to Chinese 🇨🇳