Edit Models filters

Apps

Docker Model Runner

Inference Providers

HF Inference API

Misc

Inference Endpoints

text-generation-inference

4-bit precision

8-bit precision

text-embeddings-inference

Carbon Emissions

Mixture of Experts

Models

28

Full-text search

Active filters: kernel

Motif-Technologies/optimizer

Updated Jun 23 • 19

RedHatAI/quantization

Updated 3 days ago • 5

kernels-community/flash-attn3

Updated about 23 hours ago • 9

RedHatAI/moe

Updated 5 days ago • 1

kernels-community/flash-attn

Updated 20 days ago • 11

kernels-community/activation

Updated 8 days ago • 4

kernels-community/paged-attention

Updated 7 days ago • 2

kernels-community/mamba-ssm

Updated about 20 hours ago

kernels-community/quantization-eetq

Updated about 23 hours ago

kernels-community/rotary

Updated about 23 hours ago

kernels-community/flash-mla

Updated Jun 4 • 1

kernels-community/triton-scaled-mm

Updated May 6 • 1

kernels-community/triton-layer-norm

kernels-community/deformable-detr

Updated about 23 hours ago

medmekk/LlamaRMSNorm-triton

medmekk/rmsnorm

medmekk/triton-llama-mlp

medmekk/triton-llama-attn

kernels-community/liger_kernels

kernels-community/punica-sgmv

Updated about 23 hours ago

Motif-Technologies/activation

Updated 1 day ago • 18

cdreetz/kwen2.5-1.5b

Text Generation • 2B • Updated Jun 4 • 18

kernels-community/megablocks

Updated 6 days ago • 1

EricB/kernels-paged-attention-metal

Updated Jun 26 • 1

drbh/img2gray

cdreetz/kwen2.5-1.5b-v2

Text Generation • 2B • Updated 12 days ago • 68

kernels-community/metal-flash-sdpa

Updated 6 days ago • 1

medmekk/triton-flash-attn-sink-clone

Updated 6 days ago