conftrace_

parallel transformer

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

time to first token (1) multi-device inference (1) tensor parallelism (1) parallel generation (1) continuous integrate-and-fire (1) inference latency (1) speech recognition (1)

Papers

Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference NeurIPS 2024 Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition Interspeech 2022