Inference & Serving · 2025

Defeating Nondeterminism in LLM Inference

Horace He

Traces run-to-run nondeterminism in LLM serving to batch-size-dependent kernel reductions rather than float non-associativity, and gives batch-invariant RMSNorm/matmul/attention kernels that make inference bitwise-reproducible.

Editorial record

Plain-language summary

Traces run-to-run nondeterminism in LLM serving to batch-size-dependent kernel reductions rather than float non-associativity, and gives batch-invariant RMSNorm/matmul/attention kernels that make inference bitwise-reproducible.

Knowledge graph

Relationships

Descendants

Source record

Provenance

Record ID
P-655
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.