Embla1-4bit, WebGPU step graph
The ONNX graph that runs prefill for Embla 1 on WebGPU (live demo), a browser engine for
sevren-ai/Embla1-4bit. One step of the model (a prefill chunk of up to 64
tokens, or one decode token) with the KV / engram-conv cache as explicit inputs and outputs, exported from the PyTorch reference
and rewritten for onnxruntime-web's WebGPU execution provider.
embla_step.onnx+embla_step.onnx.data(0.48 GB): the non-expert weights in MLX's 4-bit format, asMatMulNBitswith an exact offset term for the affine bias.- The routed experts (3.9 GB) are graph inputs, not part of this repo. The engine streams them from
sevren-ai/Embla1-4bit/model.safetensors. The engram rows are an input too (looked up in that repo'sengram_table.safetensors).
Build: sh tools/build_graph.sh in the GitHub repo (export + four graph rewrites, documented there).
Model by sevren.ai, MIT licensed. This is a derived format of their weights, under the same license.
Model tree for rasgaard/Embla1-4bit-webgpu
Base model
sevren-ai/Embla1-4bit