127 citations · 127 across the 7 of their papers we have counts for
7 papers
INT-FlashAttention: Enabling Flash Attention for INT8 Quantization
Shimao Chen, Zirui Liu, Zhiying Wu +6
As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention…
ISO: Overlap of Computation and Communication within Seqenence For LLM Inference
Bin Xiao, Lei Su
In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential exec…
Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation
Lujun Gui, Bin Xiao, Lei Su +1
Lossless speculative decoding accelerates target large language model (LLM) inference by employing a lightweight draft model for generating tree-structured candidates, which are su…
BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline
Guosheng Dong, Da Pan, Yiding Sun +17
The general capabilities of Large Language Models (LLM) highly rely on the composition and selection on extensive pretraining datasets, treated as commercial secrets by several ins…
Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding
Bin Xiao, Lujun Gui, Lei Su +1
Large Language Models (LLMs) frequently suffer from inefficiencies, largely attributable to the discord between the requirements of auto-regressive decoding and the architecture of…
Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge
Bin Xiao, Chunan Shi, Xiaonan Nie +5
Large language models (LLMs) suffer from low efficiency as the mismatch between the requirement of auto-regressive decoding and the design of most contemporary GPUs. Specifically,…
Baichuan 2: Open Large-scale Language Models
Aiyuan Yang, Bin Xiao, Bingning Wang +52
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing…