ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)
☆28Sep 29, 2026Updated 3 weeks ago
Alternatives and similar repositories for H3-V100
Users that are interested in H3-V100 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆31Aug 29, 2026Updated last month
- Mixed-precision acceleration patch for MiniMax H3 inference on NVIDIA V100☆39Sep 6, 2026Updated last month
- Run MiniMax H3 at native fp16 on pre-bf16 GPUs (V100/Volta) — exact-math fix for the black-frame overflows, ~11× faster than the fp32 fal…☆55Aug 8, 2026Updated 2 months ago
- A ComfyUI custom node enabling **Flash Attention 1** on legacy NVIDIA GPUs (Tesla V100, T4) that lack Compute Capability 8.0+ required by…☆31Feb 9, 2026Updated 8 months ago
- OpenReel Studio source snapshot☆34Aug 17, 2026Updated 2 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Strata port for Tesla V100 (sm_70): Qwen3.8-Flash-Next with 262K context and MTP☆84Updated this week
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区，聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆26Jul 2, 2026Updated 3 months ago
- SGLang for cool dudes using V100☆79Oct 5, 2026Updated 2 weeks ago
- Use your ChatGPT subscription in DeepSeek Harness through OpenAI's Codex sign-in flow☆82Sep 29, 2026Updated 3 weeks ago
- Hand-written NVFP4 W4A16 CUDA kernels for Volta☆175Aug 19, 2026Updated 2 months ago
- 本地豆包多账号文生/图生视频管理器☆69Jul 15, 2026Updated 3 months ago
- Enables the ComfyUI MiniMax H3 reference-to-video workflow to use a stronger FL2VA model and validated Ref2VA tensor-overlay modes to unl…☆31Sep 25, 2026Updated 3 weeks ago
- Fast & lightweight interface for running Nano Banana LLM and compact local models on your PC. Optimized for high-speed AI interactions.☆44Mar 17, 2026Updated 7 months ago
- MiniMax H3 300% speed本地部署指南（消费级 16GB 显存版）：全栈加速链 cu130+SageAttention+TE-Speed 实测、模型组合、避坑清单☆85Aug 12, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆48Aug 6, 2026Updated 2 months ago
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆57Aug 6, 2026Updated 2 months ago
- A focused, keyboard-first DeepSeek coding agent built on the plugin architecture of DeepSeek Harness and inspired by the interaction qual…☆33Updated this week
- xy-自由画布☆32Jun 1, 2026Updated 4 months ago
- MiniMax-H3 Fun ControlNet for ComfyUI. Depth, canny, pose, HED or MLSD video driving H3 frame by frame, built on ComfyUI's own H3 blocks.☆48Sep 15, 2026Updated last month
- GGUF Quantization support for native ComfyUI models☆95Updated this week
- GPT娘额度挂件：Windows / macOS 白发龙娘桌面挂件，自动识别 Free、Go、Plus、Pro 等套餐，按实际额度窗口显示，支持单行居中、语录、按压反馈、拖动缩放和主窗口跟随。☆174Updated this week
- Local AI speech-to-text, powered by GGML. C++17 port of Qwen3-ASR (Qwen team, Alibaba). 30 languages and 22 Chinese dialects, any input r…☆22Updated this week
- Cockpit web UI for the omp (oh-my-pi) coding agent. Multi-session chat, kanban, cron routines, inbox, Telegram bridge, plugin marketplace…☆24May 29, 2026Updated 4 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Codex Agent skills for MV storyboard direction and MiniMax H3 production orchestration.☆23Aug 11, 2026Updated 2 months ago
- Slate — Local previs workbench for AI short films. One storyboard.json drives the whole pipeline: film analysis → script → shots → assets…☆48Oct 7, 2026Updated 2 weeks ago
- 个人工作台搭建skill☆40Aug 4, 2026Updated 2 months ago
- llama.cpp optimized for NVIDIA Tesla V100 (SM70): large MoE Qwen3.8-Flash-Next with MTP (prefill 3464 tok/s at 200K context, 6x V100-16GB…☆44Updated this week
- Minimax video audio Concat AV Latent for any video into Minimax H3 sampler☆71Aug 6, 2026Updated 2 months ago
- ☆51Aug 3, 2026Updated 2 months ago
- 1CatV2 with TileLANG written FA-v100 and many goodies☆20Jul 15, 2026Updated 3 months ago
- ☆16Sep 6, 2026Updated last month
- Local Codex-style desktop GUI for the Pi coding agent☆32Jun 29, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
- Cross-platform screen & system-audio capture for Rust. Raw frames + real metadata from native backends: PipeWire/X11, ScreenCaptureKit, D…☆34Updated this week
- 自动化AI视频创作，纯本地部署。集成本地ComfyUI，集成主流的工作流MiniMax-H3、LTX2.3、Qwen-Image、Krea2等等。包含图片、音频、音乐、视频创作，告别繁琐的ComfyUI工作流。致力于打造一款真正的AI短剧生产力工具。☆41Updated this week
- On-demand Services/Data marketplace for AI Agents.☆11Feb 14, 2025Updated last year
- forked from vllm-project/flash-attention☆69May 9, 2026Updated 5 months ago
- Feed an idea (plus optional reference images) and get Minimax H3 prompt — with shots, camera vocabulary, dialogue tags, soundscape, and m…☆108Aug 9, 2026Updated 2 months ago
- Web UI for Oh My Pi (omp) coding agent | Oh My Pi 编程智能体的 Web 可视化界面☆37Aug 4, 2026Updated 2 months ago