Transmuter ⚗️

Transmuter runs Hugging Face ONNX models on any Nx backend, with no per-architecture code. Use EMLX on Apple silicon, or EXLA on CUDA or on the CPU.

The goal of Transmuter is to implement the ONNX operators in Nx. Then ONNX models run without model code.

An ONNX file contains a graph of operators. An operator is one small, standard computation, such as MatMul, Conv, Softmax, Add or Reshape. Each operator has inputs, outputs and attributes, for example the kernel size of a Conv. The ONNX standard defines about 200 operators, and a model connects a few hundred to a few thousand of them. When a model is exported, the exporter traces its forward pass and writes these operators to the file.

Transmuter implements each operator one time, as Nx operations. It then runs a model by running its graph, operator by operator. So Transmuter does not port model architectures. A new architecture needs no new Elixir code. It needs only operators that Transmuter already has.

The gap

Elixir has three ways to run Hugging Face models today. Each way has a limit:

• Bumblebee runs models with great accuracy on all Nx backends. But a person must port each architecture to Axon by hand, and a port takes weeks of work and review. Hugging Face gets new architectures faster than people can port them.
• Ortex runs ONNX models with ONNX Runtime. But it runs outside of Nx: you cannot put it in a defn function, it has no Apple silicon GPU path, and it is in maintenance mode.
• axon_onnx changed ONNX graphs into Axon models. It stopped in 2024. It set all shapes when it loaded a model, and many ONNX graphs need shapes that change.

Transmuter fills this gap. It runs the exported graph directly as Nx operations, so:

• Models that Bumblebee does not have run with no new code. Examples are SAM, Depth Anything, Grounding DINO, OWLv2, Florence-2, RF-DETR, Kokoro and Stable Diffusion.
• The result is plain Nx. It runs on EMLX and EXLA, it works with Nx.Serving, and Nx.Defn.grad can differentiate it.
• Shapes are set when the function compiles, not when the model loads. Thus decoders with a KV cache and graphs with If branches work.

When a model has no ONNX file on Hugging Face, export it one time with Optimum. In the 300 most downloaded transformers models, 62% of downloads already have an ONNX file on Hugging Face.

Example

Transmuter.Text gives servings that take text, as in Bumblebee. A serving loads the ONNX file, the tokenizer and the configuration of a Hugging Face repository, and returns an Nx.Serving:

opts = [backend: EMLX.Backend, defn_options: [compiler: EMLX]]

serving = Transmuter.Text.text_embedding({:hf, "Xenova/all-MiniLM-L6-v2"}, opts)
Nx.Serving.run(serving, "The cat sat on the mat.")
#=> %{embedding: #Nx.Tensor<f32[384] ...>}

serving = Transmuter.Text.generation({:hf, "onnx-community/Qwen3-0.6B-ONNX"}, opts)
Nx.Serving.run(serving, %{messages: [%{role: "user", content: "What is the capital of France?"}], seed: 7})
#=> %{results: [%{text: "<think>\n...</think>\n\nThe capital of France is **Paris, France**.",
#=>               token_summary: %{input: 15, output: 167, padding: 0}}]}

The text tasks are text_embedding, text_classification, token_classification, fill_mask and generation. Their results have the shapes of Bumblebee, and their values match the pipelines of Python transformers. See the Pipelines guide.

Tensors

For a model that has no serving, give tensors to the graph:

model = Transmuter.load!({:hf, "Xenova/all-MiniLM-L6-v2", "onnx/model.onnx"}, backend: EMLX.Backend)

inputs = %{
  "input_ids" => Nx.tensor([[101, 7592, 2088, 102]]),
  "attention_mask" => Nx.tensor([[1, 1, 1, 1]]),
  "token_type_ids" => Nx.tensor([[0, 0, 0, 0]])
}

run = Transmuter.compile(model, inputs, compiler: EMLX)
%{"last_hidden_state" => hidden} = run.(inputs)

# Sentence embedding: mean of the token vectors, then L2 normalization.
mask = Nx.new_axis(inputs["attention_mask"], -1)
embedding = Nx.sum(Nx.multiply(hidden, mask), axes: [1]) |> Nx.divide(Nx.sum(mask, axes: [1]))
embedding = Nx.divide(embedding, Nx.LinAlg.norm(embedding, axes: [1], keep_axes: true))

The export sets the names of the inputs and outputs. model.inputs and model.outputs show them. For this export, model.outputs is ["last_hidden_state"].

Transmuter runs the graph that is in the file, and nothing more. The graph of all-MiniLM-L6-v2 stops at the token vectors, because sentence-transformers adds the pooling outside of the model. Thus the example above does the pooling. Transmuter.Text.text_embedding/2 does the tokenization, the pooling and the batching for you.

Transmuter.compile/3 compiles the model for the shapes of the inputs that you give. The function that it returns also takes inputs of other shapes: it compiles them on their first call, and keeps the most recently used shapes compiled. The :cache_size option sets how many, and the default is 8.

Transmuter.run/4 is the function that Transmuter.compile/3 compiles. It reads the ONNX graph and calls one Nx function for each operator. You can use it in two ways:

• Call it directly. Each operator runs immediately, one after the other. This is eager execution. It is slower, but the model can read values while it runs.
• Give it to Nx.Defn.jit/2 or Nx.Defn.value_and_grad/2. Nx then records the operators as one graph, and the backend compiles that graph.

Text to speech with Kokoro

bench/kokoro_tts.exs runs Kokoro-82M from its ONNX export and writes a WAV file. All operators of the export run in Transmuter. The example also shows how to round audio lengths to 200 ms buckets to limit recompilation.

Kokoro reads phonemes, not text. Elixir has no phonemizer yet, so the example contains phonemes that were made in advance. See the Speech and Audio guide for more models and patterns.

The example also fixes one node of the export. The export computes the STFT phase with the atan2 of torch.onnx, which gives -π for atan2(0, x) when x is negative. torch.atan2 gives π, and the model was trained with π. Transmuter computes an exact STFT, so the imaginary part is 0 at DC and Nyquist, and the wrong phase in every frame adds a tone at 4.8 kHz. ONNX Runtime hides the error, because its STFT has small rounding errors at these bins. The example changes the Greater test of the atan2 to GreaterOrEqual, as in torch.atan2.

Installation

def deps do
  [
    {:transmuter, "~> 0.1"},
    {:emlx, "~> 0.5"},
    {:tokenizers, "~> 0.5"}
  ]
end

Use EXLA instead of EMLX for CUDA. The Transmuter.Text servings need tokenizers. Chat templates need minijinja_ex with its Hugging Face compatibility, which is not released yet: add {:minijinja_ex, github: "georgeguimaraes/minijinja_ex", branch: "feat/chat-template-compat"} and set MINIJINJA_EX_BUILD=1 to build it.

Compilation and graph breaks

Some graphs use a tensor value to set a shape or to select a branch. Transmuter.compile/3 breaks the graph at these operators, runs the break eagerly on the real values, and compiles the next segment for the shapes the values decide. Compiled segments are cached by input shapes.

See the Compiling and Graph Breaks guide for a full explanation of graph breaks, static inputs, the :cache_size option, EMLX memory management, and how to read error messages.

Non-tensor values and random operators

Nx tensors hold only numbers. Transmuter keeps string tensors, sequences, and empty optionals as Elixir terms. Give string and sequence inputs as :static_inputs. A compiled function returns only tensors. To read string or sequence outputs, call Transmuter.run/4 without compilation. Random operators draw from Nx.Random, and each call of a compiled model draws new values. ImageDecoder needs the optional stb_image dependency.

See Supported Operators and Data Types for details.

Telemetry

Transmuter emits :telemetry events when it loads, compiles and runs a model. The graph break events show which segment compiles again and for which shapes, which segment the cache evicts, and how long each break operator runs. Transmuter.Telemetry lists each event with its measurements and metadata.

To log the compile work, attach the logger when your application starts:

Transmuter.Telemetry.Logger.attach()

Precision and quantization

Half-precision exports run in f32 by default, as in ONNX Runtime on the CPU. compute_type: nil runs them in native f16 or bf16 with half the memory, but some exports overflow in native f16. With backend: EMLX.Backend, 4-bit and 8-bit MatMulNBits weights stay packed as MLX quantized tensors for lower peak memory and faster inference.

See the Backends and Performance guide and the Language Models guide for details and benchmarks.

Fine-tuning

Transmuter.run/4 is plain Nx. Thus Nx.Defn.value_and_grad/2 calculates gradients through the graph, and an optimizer such as Polaris updates the params. Load the model with trainable: true. Then small weights, such as a bias with 1 element, are params and not constants.

bench/finetune.exs fine-tunes a MiniLM cross-encoder. Its gradients and its loss curve for 30 AdamW steps are the same as in PyTorch.

Fine-tune an fp32 export. Inference exports have no dropout, and quantized weights have no gradients.

Coverage

bench/coverage runs the most downloaded ONNX exports for each Hugging Face task. It compares each output with ONNX Runtime. The reference is ONNX Runtime with graph optimizations off, because its default optimizer gives wrong results for some exports. For MatMulNBits, the reference uses accuracy_level 0. At level 4, ONNX Runtime quantizes the activations to int8, and that result is an approximation.

Transmuter supports all 203 operators of the ONNX standard domain, and the ONNX Runtime contrib operators that Hugging Face exports use, including the mixture-of-experts operators MoE and QMoE.

Three models do not match value by value, because they make small rounding differences large:

• Grounding DINO selects 900 of 13,294 queries with TopK, and some scores differ by only 9.5e-7. All operators before TopK match. On a real image with a text prompt, Transmuter gives the same detections as ONNX Runtime, with scores within 0.0001.
• The Gemma 4 E2B decoder has activations up to about 1300 and final norm weights up to about 700. When the test changes the float inputs of ONNX Runtime by 1e-7 of their values, about one f32 rounding step, the logits of ONNX Runtime change by up to 5.5. The logits of Transmuter differ from ONNX Runtime by 5.3 on the CPU and by 13.6 on the GPU, which is the same noise. The two give the same token for 7 of 8 positions of the random test input.
• Kokoro sums a phase over all audio samples and takes its STFT. ONNX Runtime and MLX round that sum differently. Also, the atan2 of the export gives a different phase for an exact STFT than for the STFT of ONNX Runtime (see Text to speech with Kokoro). When the test gives the Sin and STFT outputs of ONNX Runtime to Transmuter, all other operators match. With the atan2 fix of the example, the spectrum of the speech matches PyTorch, with no tone at 4.8 kHz.

These models also ran from input to final result, and the result agrees with ONNX Runtime:

To run the matrix:

1. Run bench/coverage/select_models.py to select the models.
2. Run bench/coverage/record_references.py to download them and record the ONNX Runtime outputs.
3. Run bench/coverage/run_cases.py to run each case through Transmuter.
4. Run bench/coverage/print_matrix.py to show the matrix, and bench/coverage/list_models.py to make the table of tested models.

If a case does not match, run bench/coverage/trace_ort.py and bench/coverage/find_divergence.exs. They show the first node where Transmuter and ONNX Runtime give different values.

Tests

mix test downloads five models and compares them with ONNX Runtime. test/support/model_references.py shows the reference values.

mix test also runs one small graph for each operator variant in test/fixtures/ops, with no download. test/support/make_op_fixtures.py makes these graphs and records their outputs from ONNX Runtime, or from the ONNX reference evaluator when ONNX Runtime does not have the operator. For random operators, the tests check the shape, the type and the distribution of the values.

On a Mac, TRANSMUTER_TEST_DEVICE=cpu mix test uses the EMLX CPU device. But EMLX 0.5 runs compiled functions on the GPU when Metal is available, also with device: :cpu. Thus only the Linux CI tests the CPU fully.

License

Apache-2.0