Hacker News
- Implement Flash Attention Back End in SGLang – Basics and KV Cache https://hebiao064.github.io/fa3-attn-backend-basic 5 comments
Linked pages
- [1706.03762] Attention Is All You Need https://arxiv.org/abs/1706.03762 145 comments
- [2205.14135] FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness https://arxiv.org/abs/2205.14135 3 comments
- GitHub - NVIDIA/cutlass: CUDA Templates for Linear Algebra Subroutines https://github.com/NVIDIA/cutlass 0 comments
- GitHub - vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs https://github.com/vllm-project/vllm 0 comments
- FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision | Tri Dao https://tridao.me/blog/2024/flash3/ 0 comments
- [2405.04434] DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model https://arxiv.org/abs/2405.04434 0 comments
Related searches:
Search whole site: site:hebiao064.github.io
Search title: Implement Flash Attention Backend in SGLang - Basics and KV Cache · Biao's Blog
See how to search.