Laplace 3B
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Laplace 3B brings fixed-state linear attention to AWS Trainium2
AWS Machine Learning Blog reports that i14 and AWS adapted the 3B-parameter Laplace 3B model to AWS Trainium2 using native PyTorch through TorchNeuron Native, preserving its Gated Linear Attention architecture and Muon optimizer. On one trn2.48xlarge instance, the implementation trained at about 120,000 tokens per second and served 11,544 output tokens per second across 1,280 concurrent sequences. The blog says the recurrent state remains 29.5 MB per sequence regardless of context length, while warning that fixed-state compression requires workload-specific retrieval-quality evaluation.
AWS Machine Learning Blog · 🔥 0
Experience and discussion from the community
Share my Laplace 3B experienceAsk about Laplace 3B
Nobody has shared their experience with Laplace 3B yet.