flashrt/speculative-draft-primitives
• Updated • 9 • 2
Edit Kernels filters
Kernels
217
kernels-community/aiter-flash-attn-ck
• Updated • 83 • 1
kernels-community/vllm-moe
• Updated • 116
AntonV/fla
• Updated
nCompass-tech/triton-moe
• Updated • 1
kernels-community/msa
• Updated • 240
kernels-staging/finegrained-fp8
Updated
kernels-staging/vllm-flash-attn3
Updated • 3
drbh/gemmaq
• Updated • 10
kernels-staging/mamba-ssm
Updated
jaygala223/triton-layernorm
Updated • 1
AethronPhantom/Ada_Kernel
Updated
kernels-staging/tokenspeed-attention
Updated
flashrt/sageattention2-blackwell
• Updated • 51 • 1
flashrt/adaptive-layernorm-producers
• Updated • 31 • 1
adarshxs/tokenspeed-attention
• Updated
flashrt/bf16-linear-gemv
• Updated • 48 • 1
flashrt/linear-attention-seq-state
• Updated • 63 • 2
flashrt/transformer-fused-ops
• Updated • 68 • 1
flashrt/grouped-moe-gemv
• Updated • 43 • 2
JingzeShi/flash-sparse-attn
• Updated
flashrt/causal-conv1d-state
• Updated • 43 • 2
flashrt/gated-delta-attention
• Updated • 97 • 3
flashrt/fp8-kv-attention
• Updated • 39 • 1
flashrt/fp4-fused-ops
• Updated • 39 • 1
flashrt/fp4-gemm
• Updated • 45 • 1
flashrt/fp8-gemm
• Updated • 39 • 2
flashrt/linear-attention-primitives
• Updated • 36 • 2
flashrt/world-model-conv
• Updated • 35 • 1
flashrt/diffusion-step-ops
• Updated • 40 • 1