REVIEW 2 cited by
LightSeq: A High Performance Inference Library for Transformers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Transformer, BERT and their variants have achieved great success in natural language processing. Since Transformer models are huge in size, serving these models is a challenge for real industrial applications. In this paper, we propose LightSeq, a highly efficient inference library for models in the Transformer family. LightSeq includes a series of GPU optimization techniques to to streamline the computation of neural layers and to reduce memory footprint. LightSeq can easily import models trained using PyTorch and Tensorflow. Experimental results on machine translation benchmarks show that LightSeq achieves up to 14x speedup compared with TensorFlow and 1.4x compared with FasterTransformer, a concurrent CUDA implementation. The code is available at https://github.com/bytedance/lightseq.
Forward citations
Cited by 2 Pith papers
-
SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference
SeaLLM shares GPU resources across multiple LLM services with a preemptive, service-characteristic-aware scheduler, search-based placement, adaptive replacement, and a merged-block unified KV cache, cutting normalized...
-
Pie: Pooling CPU Memory for LLM Inference
Pie hides the latency of swapping KV cache layers between GPU and CPU memory behind normal computation, improving LLM serving throughput and memory efficiency on high-bandwidth interconnects.
Discussion (0). Continue with ORCID to comment.