Icme Preflight README
The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Icme Preflight listing page.
JOLT Atlas
JOLT Atlas is a zero-knowledge machine learning (zkML) framework that extends the JOLT proving system to support ML inference verification from ONNX models.
Made with ❤️ by ICME Labs.
Overview
JOLT Atlas enables practical zero-knowledge machine learning by leveraging Just One Lookup Table (JOLT) technology. Traditional circuit-based approaches are prohibitively expensive when representing non-linear functions like ReLU and SoftMax. Lookups eliminate the need for circuit representation entirely.
In JOLT Atlas, we eliminate the complexity that plagues other approaches: no quotient polynomials, no byte decomposition, no grand products, no permutation checks, and most importantly — no complicated circuits.
Our core ethos is to reduce commitment costs via sumcheck while committing only to small-value polynomials.
Examples
Examples live in jolt-atlas-core/examples/ and demonstrate end-to-end prove → verify flows for various ONNX models.
GPT-2
GPT-2 proof and verification flow.
nanoGPT
A ~0.25M-parameter GPT model (4 transformer layers). Loads the ONNX graph, generates a SNARK proof of inference, and verifies it.
Transformer (self-attention)
Single self-attention block proof.
MiniGPT / MicroGPT
Smaller GPT variants useful for quick iteration and debugging.
Benchmarks
System specs: MacBook Pro M3, 16GB RAM
GPT-2 (125M params)
GPT-2 is a 125-million-parameter transformer model from OpenAI.
JOLT Atlas
| Stage | Wall clock |
|---|---|
Proving/verifying key generation (setup_prover) | 1.003 s |
Witness + commitment phase (ONNXProof::commit_witness_polynomials) | 0.762 s |
IOP proving (ONNXProof::iop) | 5.997 s |
Reduction opening proof (excluding HyperKZG::prove) | 1.899 s |
HyperKZG prove (HyperKZG::prove) | 2.392 s |
Proof time (ONNXProof::prove) | 14.889 s |
Verify time (ONNXProof::verify) | 1.038 s |
End-to-end total (setup_prover + prove + verify) | 16.930 s |
nanoGPT (~0.25M params, 4 transformer layers)
nanoGPT is the standard workload we use for cross-project comparison. It is a ~250k-parameter GPT model with 4 transformer layers.
JOLT Atlas:
| Stage | Wall clock |
|---|---|
Verifying key generation (setup_verifier) | <0.001 s |
Proving key generation (setup_prover) | 0.263 s |
Proof time (ONNXProof::prove) | 2.288 s |
Verify time (ONNXProof::verify) | 0.127 s |
End-to-end total (setup_prover + prove + verify) | 2.678 s |
ezkl on the same model (source):
| Stage | Wall clock |
|---|---|
| Verifying key generation | 192 s |
| Proving key generation | 212 s |
| Proof time | 237 s |
| Verify time | 0.34 s |
JOLT Atlas produces a proof for nanoGPT in ~2.29 s versus ezkl's ~237 s proof time (not counting their 400+ s of key generation). That is roughly a 104× speed-up on proof generation alone.
How to reproduce locally
Add -- --trace for Chrome Tracing JSON output (view in chrome://tracing), or -- --trace-terminal for timing printed to the terminal.
Getting Started
GPT-2 (first run)
GPT-2 uses a Hugging Face–hosted ONNX model that is not checked into the repo. A helper script downloads and prepares it automatically.
- Clone the repository.
- Install Rust and Cargo.
- Download the model:
This exports GPT-2 via Hugging Face Optimum
into atlas-onnx-tracer/models/gpt2/ and copies model.onnx → network.onnx.
- Test the model (trace only, no proof):
You should see the model graph printed and an output shape like
[1, 16, 65536] (vocab size 50257 padded to the next power of two).
- Prove & verify GPT-2:
A successful run prints Proof verified successfully!.
Acknowledgments
Thanks to the Jolt team for their foundational work. We are standing on the shoulders of giants.