Edit Models filters

Showing models from

Tasks

Text Generation

Image-Text-to-Text

Parameters

Libraries

Transformers.js

Apps

Inference Providers

Hardware

Add your hardware

Models

54

Base only

Active filters: flashrt

flashrt/flashrt-spatiotemporal-layout

Updated Aug 5 • 9

flashrt/fp4-gemm

flashrt/flashrt-fp8-ffn

flashrt/flashrt-qkv-cache-rope

flashrt/causal-conv1d-state

Updated Aug 17 • 5

flashrt/flashrt-smallm-gemm

flashrt/grouped-moe-gemv

Updated Aug 17 • 101

flashrt/flashrt-fused-quant

flashrt/transformer-fused-ops

flashrt/fp4-fused-ops

Updated Aug 17 • 470

flashrt/vl-transformer-primitives

flashrt/linear-attention-seq-state

flashrt/turboquant-kv

flashrt/diffusion-step-ops

flashrt/flashrt-vla-residual-gates

flashrt/MiniMaxAI-msa-blackwell

Updated Jul 9 • 2

flashrt/linear-attention-primitives

flashrt/bf16-linear-gemv

flashrt/flashrt-vla-video

flashrt/flashrt-residual-norm-quant

flashrt/flashrt-gemm-epilogues

flashrt/flashrt-nvfp4

flashrt/world-model-conv

flashrt/fp8-gemm

flashrt/fp8-kv-attention

flashrt/gated-delta-attention

Updated Aug 17 • 3

flashrt/flashrt-fp8-swiglu-ffn

flashrt/flashrt-adaptive-norms

flashrt/adaptive-layernorm-producers

flashrt/sageattention2-blackwell