flashrt/fp4-gemm
Updated
AI & ML interests
training & inference infra
Recent Activity
flashrt/weight-only-ffn
Updated
flashrt/fp8-kv-attention
Updated
flashrt/flashrt-fp8-ffn
Updated
flashrt/flashrt-gemm-epilogues
Updated
flashrt/gated-delta-attention
Updated • 596
flashrt/transformer-fused-ops
Updated
flashrt/fa2-seqused-runtime
Updated
flashrt/turboquant-kv
Updated
flashrt/speculative-draft-primitives
Updated
flashrt/small-matrix-cholesky
Updated
flashrt/padded-fp8-producers
Updated
flashrt/linear-attention-seq-state
Updated
flashrt/linear-attention-primitives
Updated
flashrt/fused-mlp-megakernels-blackwell
Updated
flashrt/fp8-prefill-attention-blackwell
Updated • 1
flashrt/flashrt-vla-video
Updated
flashrt/flashrt-flex-attention-train
Updated
flashrt/audio-codebook-primitives
Updated
flashrt/grouped-moe-gemv
Updated • 101
flashrt/fp4-fused-ops
Updated • 470
flashrt/causal-conv1d-state
Updated • 117
flashrt/sageattention3-blackwell
Updated
flashrt/sageattention2-blackwell
Updated
flashrt/adaptive-layernorm-producers
Updated
flashrt/fp8-gemm
Updated
flashrt/masked-mha-runtime
Updated
flashrt/flashrt-qkv-cache-rope
Updated
flashrt/flashrt-adaptive-norms
Updated
flashrt/flashrt-residual-norm-quant
Updated