FlashQLA: High-Performance Linear Attention Kernels on TileLang

GitHub@Alibaba_QwenApr 29, 2026

🚀 Introducing FlashQLA: high-performance linear attention kernels built on TileLang. ⚡ 2–3× forward speedup. 2× backward speedup. 💻 Purpose-built for agentic AI on your personal devices. 💡Key insights: 1. Gate-driven automatic intra-card CP. 2. Hardware-friendly algebraic https://t.co/4Vhyyw5RuB

Views75.0k
Comments38
Reposts107
Likes936
Launched Apr 29, 2026View post

More from GitHub

1
2
3

🆕 @OpenAIDevs GPT-5.5 is now generally available and rolling out in GitHub Copilot. Our early testing shows ➡️ It delivers its strongest performance on complex agentic coding tasks ➡️ It resolves real-world coding challenges previous GPT models couldn’t Try it out in Copilot https://t.co/jLAZagNKXJ

Apr 24, 2026
Views244.0k
Comments98
Reposts55
View post
4

See all GitHub launches →