SGLang-JAX is a high-performance LLM inference engine optimized for TPU/GPU hardware using JAX. It implements continuous batching, radix tree KV cache management, FlashAttention integration, tensor parallelism, and disaggregated serving (prefill-decode separation). The system provides OpenAI-compatible API endpoints for text generation, chat, embeddings, and tool use, with support for Mixture-of-Experts models, LoRA adaptation, quantization, and speculative decoding. Architecture features modular components: tokenizer manager, scheduler, model executor, memory hierarchy (including HiCache host-device transfer), optimized JAX/Pallas kernels, and LoRA adapter management. Designed for production serving workloads on TPU infrastructure with first-party support for Qwen, Llama, Gemma, DeepSeek, and multimodal models.
HY-WU is a machine learning application for text-guided image editing that implements a Functional Neural Memory framework. The system generates instance-conditioned LoRA (Low-Rank Adaptation) weights on-the-fly from hybrid image-instruction representations and injects them into a frozen backbone model (HunyuanImage-3.0-Instruct) during forward pass, enabling test-time adaptation without optimization. The architecture centers around a WUPipeline orchestrator that coordinates a parameter generator, the base model with PG mixin integration, and image processing components. Key entry points include the infer.py CLI script and gradio/app.py web interface. The system processes user prompts and input images through VAE encoding, condition extraction, parameter generation, LoRA injection, and image decoding to produce edited outputs.
Helios is a real-time long video generation system that implements text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation using a 3D transformer architecture. The system features a modular design with specialized optimizations for performance including Ahead-of-Time Compilation (AOTI), group offloading for VRAM reduction, context parallelism (Ulysses/Ring attention), and Flash Attention kernel optimizations. It employs a multi-stage training pipeline (Base → Mid → Distilled) to balance quality and sampling speed. The repository includes a Gradio web interface (app.py) for interactive generation, command-line inference scripts, training utilities, and a comprehensive evaluation suite measuring video quality across aesthetic, motion, semantic, and naturalness dimensions. While containing research elements for ablation studies and benchmarking, its primary function is as a deployable video generation application.
UniTEX is a research-focused repository implementing a two-stage framework for high-fidelity 3D texture generation from arbitrary 3D shapes. Stage 1 uses LoRA-adapted Diffusion Transformers for multi-view texture synthesis, while Stage 2 employs a transformer-based Large Texturing Model (LTM) to predict Texture Functions in unified 3D space, bypassing UV mapping limitations. The repository integrates super-resolution (TSD_SR) for detail enhancement and provides tools for mesh processing, rendering, and texture reprojection. It includes training scripts, model architectures, and utility libraries, indicating its primary purpose is to support experimentation and reproduction of the CVPR 2026 paper's methodology rather than serving as a standalone end-user application.