Methods › Natural Language Processing › Transformers › Parallel Layers

Parallel Layers

3 papers tagged archive 2025-07-28

Introduced by Aakanksha Chowdhery et al. in PaLM: Scaling Language Modeling with Pathways

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

• Parallel Layers – We use a “parallel” formulation in each Transformer block (Wang & Komatsuzaki, 2021), rather than the standard “serialized” formulation. Specifically, the standard formulation can be written as:
y = x + MLP(LayerNorm(x + Attention(LayerNorm(x)))

Whereas the parallel formulation can be written as:
y = x + MLP(LayerNorm(x)) + Attention(LayerNorm(x))

The parallel formulation results in roughly 15% faster training speed at large scales, since the MLP and Attention input matrix multiplications can be fused. Ablation experiments showed a small quality degradation at 8B scale but no quality degradation at 62B scale, so we extrapolated that the effect of parallel layers should be quality neutral at the 540B scale.

PaperSource

Papers archive 2025-07-28

3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 26 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Auto Debugging1
Automatic Speech Recognition1
Code Generation1
Common Sense Reasoning1
Coreference Resolution1
Cross-Lingual Question Answering1
Few-Shot Learning1
Hindu Knowledge1
Known Unknowns1
Language Modeling1
Language Modelling1
Logic Grid Puzzle1
Logical Reasoning1
Math1
Memorization1
Multi-task Language Understanding1
Multiple Choice Question Answering (MCQA)1
Natural Language Inference1
Novel Concepts1
Question Answering1

Usage over time archive 2025-07-28

Papers per year tagged with Parallel Layers: 2022 to 2025, peak 1 1 0 2022: 1 paper 2022 2023: 1 paper 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections