Answers are grounded in this paper and cite their sources.
Typical optimized floatingpoint inference is not reproducible across environments: the same model on different hardware, compilers, or thread counts can produce different bits, because IEEE-754 addition is not associative and platform math libraries round transcendental functions differently (reproducible floating point is achievable, e.g. a reduction-pinned BLAS, but at a cost and not by default). We present tritify, an open-source runtime that executes the forward pass of real models -- decoder-only language models, Mixture-of-Experts decoders, and the Segment Anything 2.1 image/video stack -- with the entire run-time path (forward_int) in exact integer arithmetic; floating point is confined to offline weight/eps quantization and the float reference used for verification. We make three precise, separate claims and verify each. (1) Cross-hardware reproducibility: the integer path produces bit identical output run-to-run, across CPU instruction-set architectures, and across CPU/GPU, carried by a reproducing SHA256 of the output. (2) Decision fidelity to the float reference: the integer path reproduces the float reference's decision on the models and inputs tested, with the numeric exceptions measured rather than assumed away; we extend this to depth, measuring per-layer fidelity through sixteen layers of OLMoE-1B-7B and of a 106-billion-parameter frontier MoE, and find no fidelity cliff. (3) Location independence: because the output is a deterministic function of (weights, inputs) and is bit-identical wherever each operation runs, a model's computation can be split across CPU instruction sets, across CPU and GPU, and across many networked machines -- with zero effect on the output bits, and the gather equals the single machine exactly. We demonstrate Claim 3 at scale: a frontier Mixture of Experts model, GLM-4.5-Air (106,852,251,264 parameters, 427 GB of integer codes), generated its answer across three machines none of which can hold its full integer codes in RAM -- bit-identically to a single-host reference that streams the experts, carried by the same SHA256 at every layer (a separate run split a whole model across six machines of two instruction sets and three locations with the identical hash). The consequence is verifiable distributed inference: a fast, untrusted server (or a fleet of commodity devices) runs the model while an open scalar oracle local, or any third party rederives the exact bytes and checks them against the public reference; turning honest-run agreement into a guarantee against a dishonest server is future work. We are deliberately careful about scope: we do not claim a per-device speed improvement (distribution adds latency; the win is capacity, not speed), bit-for-bit equality of the raw floating-valued intermediates, or confidentiality verifiability is not privacy. The contribution is exactness, determinism, portability, and, above all, verifiability: every operation ships both an integer path and a floating-point reference, and a gate refuses anything the two disagree on beyond tolerance.
No takes yet. Share an insight, caveat, or question.
Sayed Amir Karim (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: