SageAttention
thu-ml
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…
Media AutomationSkill source unconfirmed
3.4KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “fast-attention”
1–7 / 7
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 7
SpargeAttn
thu-ml
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Media AutomationSkill source unconfirmed
1KGitHub
1.3KGitHub
Supertonic
supertone-inc
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Media AutomationSkill source unconfirmed
12.5KGitHub
Matcha TTS
shivammehta25
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
Media AutomationSkill source unconfirmed
1.3KGitHub
FFCreator
tnfe
A fast video processing library based on node.js (一个基于node.js的高速视频制作库)
Media AutomationSkill source unconfirmed
3.2KGitHub
IMS Toucan
DigitalPhonetics
Controllable and fast Text-to-Speech for over 7000 languages!
Media AutomationSkill source unconfirmed
2.2KGitHub