flash-mla

Here are 2 public repositories matching this topic...

📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉

📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) SRAM complexity for headdim > 256, 1.8x~3x↑🎉vs SDPA EA.

cuda attention sdpa mla mlsys tensor-cores flash-attention deepseek deepseek-v3 deepseek-r1 fused-mla flash-mla

Add a description, image, and links to the flash-mla topic page so that developers can more easily learn about it.

To associate your repository with the flash-mla topic, visit your repo's landing page and select "manage topics."