models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
flash-attn3reluflash-attn2triton-layer-normvllm-flash-attn3activationfinegrained-fp8causal-conv1dgpt-oss-triton-kernelsmamba-ssmcv-utilsmegablocksquantization-bitsandbytesflash-attn4rotaryliger-kernelsdeformable-detrpaged-attentiondeep-gemmlayer-normrwkvtriton_kernelspunica-sgmvmrayosotinygrad-rmsbitsandbytes-mpsflash-mlasage-attentionquantization-eetq