flash-mla

Here are 2 public repositories matching this topic...

📚A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, Parallelism, MLA, etc.

mla vllm llm-inference awesome-llm flash-attention tensorrt-llm paged-attention deepseek flash-attention-3 deepseek-v3 minimax-01 deepseek-r1 flash-mla qwen3

📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than 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."