Projects in Awesome Lists tagged with flash-mla
A curated list of projects in awesome lists tagged with flash-mla .
https://github.com/xlite-dev/cuda-learn-notes
📚Modern CUDA Learn Notes: 200+ Tensor/CUDA Cores Kernels🎉, HGEMM, FA2 via MMA and CuTe, 98~100% TFLOPS of cuBLAS/FA2.
cuda cuda-kernels cuda-programming cuda-toolkit cudnn cutlass flash-attention flash-mla gemm gemv hgemm
Last synced: 15 Apr 2025
https://github.com/xlite-dev/CUDA-Learn-Notes
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
cuda cuda-kernels cuda-programming cuda-toolkit cudnn cutlass flash-attention flash-mla gemm gemv hgemm
Last synced: 26 Mar 2025
https://github.com/DefTruth/CUDA-Learn-Notes
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
cuda cuda-kernels cuda-programming cuda-toolkit cudnn cutlass flash-attention flash-mla gemm gemv hgemm
Last synced: 20 Mar 2025
https://github.com/xlite-dev/ffpa-attn
📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.
attention cuda deepseek deepseek-r1 deepseek-v3 flash-attention flash-mla fused-mla mla mlsys sdpa tensor-cores
Last synced: 11 Jun 2025
https://github.com/deftruth/ffpa-attn-mma
📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) SRAM complexity large headdim (D > 256), ~2x↑🎉vs SDPA EA.
attention cuda deepseek deepseek-r1 deepseek-v3 flash-attention flash-mla fused-mla mla mlsys sdpa tensor-cores
Last synced: 06 Apr 2025
https://github.com/xlite-dev/ffpa-attn-mma
📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2x↑🎉vs SDPA EA.
attention cuda deepseek deepseek-r1 deepseek-v3 flash-attention flash-mla fused-mla mla mlsys sdpa tensor-cores
Last synced: 30 Mar 2025