Yeyun Gong, Yu Yan, Jiusheng Chen, Nan Duan, Nikhil Bhendawade, Ting Ye, Fei Hu, Desheng Cui, Bingyu Chi, Ruifei Zhang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop FastSeq framework to accelerate sequence generation without accuracy loss. The proposed optimization techniques include an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O. These optimizations are general enough to be applicable to Transformer-based models (e.g., T5, GPT2, and UniLM). Our benchmark results on a set of widely used and diverse models demonstrate 4-9x inference speed gain. Additionally, FastSeq is easy to use with a simple one-line code change. The source code is available at https://github. com/microsoft/fastseq.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.04718")
get_code_for_paper("2106.04718")
have("2106.04718")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.04718.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.04718)
Connect an agent — have() is free.