flashrt/sageattention2-blackwell
• Updated • 15 • 1
AI & ML interests
training & inference infra
Recent Activity
View all activity
flashrt/sageattention3-blackwell
• Updated
flashrt/fp8-gemm
• Updated • 36 • 2
flashrt/fp4-gemm
• Updated • 218 • 3
flashrt/masked-mha-runtime
• Updated • 24 • 1
flashrt/fp4-fused-ops
• Updated • 75 • 1
flashrt/transformer-fused-ops
• Updated • 118 • 1
flashrt/flashrt-qkv-cache-rope
• Updated • 35 • 2
flashrt/flashrt-fp8-ffn
• Updated • 42 • 5
flashrt/flashrt-residual-norm-quant
• Updated • 39 • 2
flashrt/fa4-cute-runtime
• Updated • 1
flashrt/grouped-moe-gemm
• Updated • 5 • 2
flashrt/fp8-kv-attention
• Updated • 13 • 1
flashrt/gated-delta-attention
• Updated • 69 • 3
flashrt/grouped-moe-gemv
• Updated • 51 • 2
flashrt/world-model-conv
• Updated • 24 • 1
flashrt/smallm-ffn-megakernels-blackwell
• Updated • 19 • 1
flashrt/flashrt-nvfp4
• Updated • 20 • 3
flashrt/flashrt-fused-quant
• Updated • 15 • 3
flashrt/adaptive-layernorm-producers
• Updated • 65 • 1
flashrt/weight-only-ffn
• Updated • 26 • 1
flashrt/bf16-linear-gemv
• Updated • 13 • 1
flashrt/transformer-layout-primitives
• Updated • 23 • 2
flashrt/fp8-cross-attention-blackwell
• Updated • 8 • 1
flashrt/fused-mlp-megakernels-blackwell
• Updated • 11 • 2
flashrt/audio-codebook-primitives
• Updated • 3 • 2
flashrt/flashrt-vla-residual-gates
• Updated • 22 • 3
flashrt/blockwise-fp8-producers
• Updated • 9 • 1
flashrt/diffusion-step-ops
• Updated • 31 • 1
flashrt/flashrt-spatiotemporal-layout
• Updated • 11 • 2