NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured 1.14–1.44× vs SageAttention and −37% MLP peak VRAM on H3
☆155Aug 13, 2026Updated 2 months ago
Alternatives and similar repositories for ComfyUI-sol-attn
Users that are interested in ComfyUI-sol-attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆323Sep 18, 2026Updated 3 weeks ago
- Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip s…☆694Updated this week
- MiniMax-H3超级缓存加速插件☆334Aug 3, 2026Updated 2 months ago
- MiniMax H3全能参考插件，B站/Youtube：在下鱼酥☆92Oct 9, 2026Updated last week
- ☆491Sep 7, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- 🚀 现代化工程级大模型通用注册机：多线程高并发 · 独立邮箱收发 · 双模抗风控 · 智能 IP 轮换 · 批量导入 CPA · Web 控制台 | Production-ready AI registration & credential platform☆88Sep 22, 2026Updated 3 weeks ago
- MiniMaxH3_LatentUpscaler for ComfyUI☆264Aug 17, 2026Updated 2 months ago
- ☆40Updated this week
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆527Updated this week
- qwen3/qwen3.5/qwen3.8/gemma4 图片反推,提示词,本地多轮对话,本地skill使用,扩写高速版☆254Sep 22, 2026Updated 3 weeks ago
- MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities [ICML 2026]☆68Updated this week
- ☆244Sep 15, 2026Updated last month
- ComfyUI nodes for JoyAI-Echo: faithful bf16 implementation with multi-shot audio-video generation☆35Jun 7, 2026Updated 4 months ago
- Single neuron simulator/ prediction benchmark; uses Hodgkin-Huxley with novel mechanisms☆47Aug 12, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Deep, Evolving Environments for Computer-Use Agents☆41Oct 9, 2026Updated last week
- Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and lin…☆104Sep 27, 2026Updated 2 weeks ago
- A rust port of con-leche☆31Updated this week
- MoJev: typed, calibrated decisions in one forward pass.☆29Sep 23, 2026Updated 3 weeks ago
- ☆88Jun 27, 2026Updated 3 months ago
- This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.☆38Updated this week
- Instella MoE is a fully open state-of-the-art Mixture-of-Experts language model, trained end-to-end on AMD Instinct™ GPUs.☆80Sep 2, 2026Updated last month
- BarunLM-35M: a parameter-efficient 35M base language model trained on 5.7B tokens☆73Aug 5, 2026Updated 2 months ago
- ComfyUI nodes to save time and keep your workflows tidy. Bundle multiple wires into one wire. Create customizable presets nodes.☆107Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Harn is a programming language and runtime for building AI agents.☆27Updated this week
- AI生图工作台 (AI Image Generator)、视频工作台。支持 Agent 与工作台模式、无限画布、素材管理、提示词反推/广场及 PWA，支持外链式配置；可接入 Grok、GPT Image 2 等自定义模型生图。自适应手机端。☆154Sep 25, 2026Updated 3 weeks ago
- Create AI videos with Claude Code, Codex, Cursor, and Grok Build, with no extra generation fees beyond the plans you already pay for☆29Aug 9, 2026Updated 2 months ago
- ☆39Sep 6, 2026Updated last month
- A place for me to dump a variety of scripts from over the years.☆13Mar 20, 2026Updated 6 months ago
- ☆183Updated this week
- Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation☆40Oct 9, 2026Updated last week
- A char-level transformer trained from scratch on an $8 ESP32-S3. Not inference: the chip runs the full training loop, with backprop writt…☆89Aug 26, 2026Updated last month
- srt subtitle translator using openai's chatgpt☆11Sep 17, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 publ…☆90Aug 19, 2026Updated last month
- A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, …☆78Oct 1, 2026Updated 2 weeks ago
- Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.☆172Aug 25, 2026Updated last month
- 蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek H…☆53Sep 30, 2026Updated 2 weeks ago
- Official Repository of Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories☆116Updated this week
- ☆16Jul 18, 2026Updated 2 months ago
- ☆41Aug 16, 2026Updated 2 months ago