ComfyUI custom node: run MiniMax H3 at near-fp16 speed with near-fp32 numerical stability on GPUs without bf16/fp8 hardware (V100 sm_70)
☆19Aug 22, 2026Updated 2 months ago
Alternatives and similar repositories for ComfyUI-MiniMaxH3-FP16Safe
Users that are interested in ComfyUI-MiniMaxH3-FP16Safe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Mixed-precision acceleration patch for MiniMax H3 inference on NVIDIA V100☆40Sep 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…☆56Aug 8, 2026Updated 2 months ago
- LTX Director 2.5☆17Aug 12, 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…☆33Feb 9, 2026Updated 8 months ago
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆35Aug 29, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Standalone multi-reference image conditioning for LTX-2.5 in ComfyUI, with MSR LoRA slot embeddings and negative temporal offsets.☆41Sep 24, 2026Updated last month
- 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
- ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)☆30Sep 29, 2026Updated 3 weeks ago
- Solving CartPole-v1 environment in Keras with Actor Critic algorithm an Deep Reinforcement Learning algorithm☆12May 19, 2020Updated 6 years ago
- SGLang for cool dudes using V100☆80Oct 5, 2026Updated 3 weeks ago
- ☆11Nov 25, 2025Updated 11 months ago
- ☆13Dec 3, 2025Updated 10 months ago
- forked from vllm-project/flash-attention☆69May 9, 2026Updated 5 months ago
- 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
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- NVIDIA Tesla V100 显卡驱动自动化管理套件☆32Oct 9, 2025Updated last year
- 扩展加载lora的路径，不用只放在本地的loras文件夹内，可自定义多个lora文件夹，或直接读路本地绝对lora路径☆13Oct 24, 2025Updated last year
- 1CatV2 with TileLANG written FA-v100 and many goodies☆20Jul 15, 2026Updated 3 months ago
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 months ago
- a tutorial demo of pomelo and bearcat☆10Jan 20, 2017Updated 9 years ago
- ReShot depth maps as ComfyUI nodes: copy a reference shot's choreography and camera into Seedance, MiniMax H3 or Wan - not the actors. By…☆14Sep 13, 2026Updated last month
- Top level CedarEDA integration package☆29Oct 22, 2024Updated 2 years ago
- ☆14May 20, 2026Updated 5 months ago
- Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, iFlow as an OpenAI/Gemini/Claude/Codex compatible API service, allow…☆10May 25, 2026Updated 5 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.
- Stashify, encrypted provider-agnostic storage using Telegram, Discord, and other third-party services as storage backends.☆18Aug 22, 2026Updated 2 months ago
- The desktop native Qt front-end for ComfyUI☆19Updated this week
- A standalone application for installing, launching, updating, repairing, inspecting, exporting, importing, and sharing ComfyUI installati…☆18Aug 21, 2026Updated 2 months ago
- Sparse-Linear Attention (SLA) nodes for ComfyUI☆13Dec 27, 2025Updated 10 months ago
- DeepSeek-V4.1-Flash (552B MoE) on one RTX 5090 with a llama.cpp fork: report, tools, results☆17Sep 23, 2026Updated last month
- Fast Windows disk space analyzer with treemap, sunburst, search and scan history.☆16Sep 20, 2026Updated last month
- A minimalist HDR image viewer optimized for large images☆14Updated this week
- Desktop app to organize, split, and backup your AI prompts and generated-image library.☆15Jun 9, 2026Updated 4 months ago
- Custom nodes for ComfyUI - Text Permutation, Loop nodes, Parameter Overlay, Visual Widgets☆16Aug 15, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- https://forum.katalon.com/t/taking-entire-page-screenshot-using-ashot-in-katalon-studio/12429☆12Jun 25, 2021Updated 5 years ago
- An elegant, premium, high-performance remote bypass and wire-management nodes suite for ComfyUI.☆14Sep 25, 2026Updated last month
- 🏆 Won Hack the Valley 2026 · Browser extension that saves and exports your AI chats, then resumes them in a fresh chat so you never lose…☆15Aug 10, 2026Updated 2 months ago
- Generative video re-detailer and 4K upscaler for ComfyUI on LTX-2.5. Refine mode (Refine-Details IC-LoRA, tiled, 4K on a 32GB card) is th…☆13Oct 13, 2026Updated 2 weeks ago
- Native INT8/W4A4 quantization + SVDQuant for Krea 2 on ComfyUI, tuned for Ampere GPUs☆13Aug 20, 2026Updated 2 months ago
- Awakening Spatial Intelligence in Unified Multimodal Understanding and Generation☆14Apr 18, 2026Updated 6 months ago
- Reason-then-encode for Krea 2: the encoder's own Qwen3-VL rewrites your prompt or reads a reference image (describe → filter → combine) b…☆18Jul 8, 2026Updated 3 months ago