ROLV Primitive©

A drop-in matmul operator that delivers up to 106× faster AI inference and up to 99% less energy on the same hardware — with bit-identical output.

Run the benchmark from any device — no install

Go to rolv.ai, sign in, pick a model from the dropdown, click run. Compute happens on our server via the public benchmark API (see rolvai/benchmark). A SHA-256 signed receipt arrives in your inbox with per-case speedup, energy reduction, correctness check, and a run hash bound to your hardware fingerprint.

Works on a laptop. Works on a Chromebook. Works on a phone. Takes about two minutes. The receipt is cryptographically tied to your run — it cannot be copied from another benchmark, and cannot be fabricated without actually running.

ROLV does not send newsletters. One-time receipt email. That's it.

Selected results on real HuggingFace weights

NVIDIA B200, BF16, TF32 on, 1,000 iterations:

Model	Natural sparsity	vs cuBLAS	vs cuSPARSE	Energy reduction
Llama-4-Scout	93.8%	4.75×	103×	79%
Mixtral-8×7B	75.0%	1.86×	109×	46%
Qwen3-30B-A3B	93.8%	3.43×	32×	71%
OLMoE-1B-7B (H200)	87.5%	2.49×	43×	60%

Intel i7 laptop (4 cores, 68 GB RAM, MKL baseline):

Model / Layer	Sparsity	vs MKL
Llama-3.2-1B down_proj	99%	106.65×
Qwen2.5-7B gate_proj	95%	59.70×
Mistral-7B q_proj	95%	21.45×

Full per-case data with SHA-256 hashes: rolv.ai/rolv_benchmarks.pdf

Why it works

Modern AI weight matrices are mostly zero. In an MoE model like Mixtral or DeepSeek-V3, 75–97% of weights are architecturally inactive for any given token — guaranteed by the router, known before computation. Standard libraries compute them anyway. ROLV identifies the non-zero structure at load time and restricts computation to live elements only. Same BLAS/tensor-core primitive, same output — on a matrix proportional to the non-zero fraction. Results are placed in the correct positions of the full output tensor. Final output is bit-identical to the full dense operation.

Inner mechanism is Patent Pending.

Verification protocol

Every benchmark case is produced with five independent verification layers:

Real HuggingFace weights — downloaded from public repositories, no synthetic matrices
Vendor baseline — Intel MKL on CPU, cuBLAS on GPU, cuSPARSE at high sparsity
Four SHA-256 hashes per case — input matrix, input vector, vendor output, ROLV output
Perturbation test — one weight altered by 10⁻³, output hash must change (rules out cached answers)
Signed run hash — SHA-256 over speedup, timestamp, and hardware fingerprint

ATOL = 0.05 on column-normalised fp64. The correctness check and the speed measurement are the same execution — you cannot skip work to game the clock without failing correctness.

1,684 / 1,684 GPU PASS · 332 / 332 CPU PASS

Independently validated by the University of Miami Frost Institute for Data Science and Computing — bit-identical SHA-256 hashes across CPU, GPU, and TPU. No commercial relationship. Validation letter.

Hardware compatibility

Validated today: NVIDIA (B200, H200, H100, A100, RTX series, T4, V100) · AMD (MI300X, MI250X, RX 7900) · Intel CPU (MKL, AVX-512) · AMD EPYC · ARM Neoverse · Apple Silicon (M1–M4 Pro) · Google TPU (v4, v5)

Framework support: PyTorch · JAX · TensorFlow · ONNX Runtime · TensorRT · vLLM · HuggingFace Transformers

Works with: BF16, FP16, FP32, INT8 checkpoints. No retraining. No re-quantisation.

On-premise evaluation

The public benchmark at rolv.ai proves the output. To run ROLV on your own hardware, against your own models, in your own environment, two NDA-gated tiers are available:

Secure Container — Hardware-locked Docker container. RolvKey™-authenticated. Processor fingerprint binding at first run; will not execute on any other machine. Optional Intel SGX hardware encryption for regulated environments. Evaluation licence + NDA required.

Direct Hardware — Single authenticated file for bare-metal servers and air-gapped environments where Docker is not permitted. Processor-bound binary with live heartbeat attestation. Evaluation licence + NDA required.

Both tiers return cryptographically signed per-run results bound to your processor fingerprint.

Contact: rolv@rolv.ai

Citation

@software{heggenhougen_rolv_2026,
  author = {Heggenhougen, Rolv E.},
  title = {ROLV Primitive©: A Universal Compute Primitive for Sparse AI Inference},
  year = {2026},
  publisher = {Zenodo},
  doi = {10.5281/zenodo.19221455},
  url = {https://rolv.ai}
}

rolvai
/

rolv-primitive