Quality-first local MiniMax H3 video-series generation and loopback API for dual RTX 4090 workstations, with native audio, references, P8/P9 continuity, and preserved artifacts.
-
Updated
Oct 15, 2026 - Python
Quality-first local MiniMax H3 video-series generation and loopback API for dual RTX 4090 workstations, with native audio, references, P8/P9 continuity, and preserved artifacts.
Research preview for reproducible MoE routing and memory oversubscription on consumer GPUs. Not a production inference engine.
DualDeadline adds separate gate/up and down-projection transfer deadlines to exact MoE offloading, with H200 validation and Triton-optimized predictors.
Deploying personal-grade production models on a consumer-grade PC
Flash-backed mixture-of-experts inference on Apple devices with Swift/MLX.
Isaac-lite for weak laptops: YAML scenes, lidar/camera/IMU sensors, synthetic datasets, plus layer streaming for models too big for your GPU
A research toolbox for running and studying LLMs on constrained hardware, with memory, placement, inference, and benchmarking methods.
LatchMoE CUDA:面向 vLLM 与 PIECEWISE CUDA Graph 的 MoE 专家卸载插件,支持固定槽位缓存、活跃专家去重批量搬运与异步预取
Local AI on Windows: Qwen 27B GGUF + Qwen-Image via llama.cpp and ComfyUI. 12GB VRAM / 16GB RAM, serial inference, automatic model switching, text-to-image and reference-image editing. 小显存本地大模型与生图工作流。
面向昇腾 NPU(vllm-ascend-hust)的 MoE 专家权重卸载插件,支持固定槽位规划、Hit/Miss 多阶段切分与异步预取
Research artifact for Memory-Sovereign Inference: Output-Exact Execution Beyond Full Residency
Stream PyTorch model blocks from NVMe or pinned CPU memory with a bounded GPU residency budget. LoRA-finetune models far larger than host RAM on one GPU - Qwen3-VL-32B and gpt-oss-120b train in under 6 GB of VRAM.
BriskMoE:面向单卡 MoE 权重卸载的非侵入式 vLLM 推测解码加速插件(Qwen3-30B 4.80× / GPT-OSS-120B 5.00× 加速)
To associate your repository with the model-offloading topic, visit your repo's landing page and select "manage topics."