QuerySplat

Spirula Studio is a cross-vendor 3D Gaussian Splatting trainer that processes photos or video into Gaussian splats and textured meshes in a self-contained binary. It combines video frame extraction, AI masking, structure-from-motion, Gaussian Splatting training, meshing, depth and normal generation, and skybox processing, with native support for fisheye and 360-degree equirectangular datasets. Its Vulkan backend runs on NVIDIA, AMD, Intel, and Apple GPUs, while a CUDA backend supports CUDA-capable NVIDIA GPUs; the application provides GUI and CLI workflows for Windows, Linux, and macOS. Quantized training is designed to support up to 10 million SH3 Gaussians in 8 GB of VRAM, and masking requires a separately downloaded SAM checkpoint.

Splash is a local inference engine for Apple silicon developed by Inco AI. It serves selected language models to coding agents and clients compatible with the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs, with streaming, tool calls, JSON Schema output, image input, and inline PDF support. Its runtime uses model-specific fused Metal kernels, weights packed for those kernels, a dedicated DFlash 2 draft model for speculative decoding, and a startup-computed memory plan for context, KV cache, and batching. The served model packages include the target model and its draft model; plain MLX or Transformers checkpoints are not supported. Splash runs locally on macOS, binds to a local HTTP server by default, and can be installed through Homebrew. The project is licensed under Apache-2.0, while model weights retain their own licenses.

LingBot-Map is a feed-forward 3D foundation model from the Robbyant Team for streaming 3D reconstruction from image sequences and video. Its Geometric Context Transformer unifies coordinate grounding, dense geometric cues, and long-range drift correction through anchor context, a pose-reference window, and trajectory memory. The system uses paged KV-cache attention for streaming inference and supports interactive browser-based reconstruction with point-cloud visualization, keyframe intervals, windowed processing for long sequences, and sky masking. It also provides an offline rendering pipeline for image folders or video, along with evaluation pipelines for datasets including KITTI and Oxford Spires. The repository reports approximately 20 FPS inference at 518×378 resolution on sequences exceeding 10,000 frames, and documents PyTorch installation with FlashInfer as the recommended attention backend and native SDPA as a fallback.

Unsloth is an open-source local desktop and web tool for running, training, fine-tuning, and deploying language, diffusion, embedding, audio, and vision models. It supports Windows, macOS, Linux, WSL, multi-GPU setups, NVIDIA, AMD, and Intel GPUs, CPUs, and the Vulkan backend. The project is distributed as Unsloth Desktop, Unsloth Studio, and Unsloth Core. It can run local models, provide an OpenAI-compatible API, connect models to agents and MCP tools, perform search and RAG, and offer remote or LAN access. Its training functions cover reinforcement learning, LoRA, QLoRA, full fine-tuning, pretraining, GRPO, DPO, and FP8, with export formats including GGUF, NVFP4, and FP8. The repository claims that its fine-tuning workflows use two times less training time and 70% less VRAM.

SGLang is an open-source serving framework and inference engine for large language models and multimodal models, developed by the SGLang project. It provides an alternative serving stack for deployed models, with runtime and kernel optimizations for inference workloads. Its documented capabilities include RadixAttention, a zero-overhead batch scheduler, cache-aware load balancing, structured-output decoding, speculative decoding, disaggregated prefill and decode, model parallelism, and support for GPU and TPU backends. The project also publishes integrations and optimizations for current open models and multimodal, image, and video-generation workloads.