AWhat changed
Introduced tile-level tensor-program abstractions and compiler optimizations to generate efficient GPU kernels for neural-network computation.
Scientific scope
Introduced tile-level tensor-program abstractions and compiler optimizations to generate efficient GPU kernels for neural-network computation. Original 2019 system used a C-based language and tile IR; the later OpenAI Python-like release is not backdated or separately counted here. Efficient kernels are not guaranteed for every workload.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original 2019 system used a C-based language and tile IR; the later OpenAI Python-like release is not backdated or separately counted here. Efficient kernels are not guaranteed for every workload.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Triton: an intermediate language and compiler for tiled neural network computations
- Tillet, Kung and Cox: Triton tile-oriented neural-network compiler — institutional research record
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction