LoMA: Lossless Compressed Memory Attention (arxiv.org)

Screenshot of arxiv.org: LoMA: Lossless Compressed Memory Attention

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Lossless LLM compression for efficient GPU inference via dynamic-length float

Lossless LLM compression for efficient GPU inference via dynamic-length float (arxiv.org)

392 points by CharlesW 1 year ago | 109 comments

arXiv paper introducing DFloat11, a lossless compression format that shrinks LLM weights by about 30% using entropy coding, with a custom GPU kernel for inference.

llm-compression dfloat11 bfloat16 entropy-coding

Screenshot of arxiv.org: Infinite Retrieval: Attention enhanced LLMs in long-context processing

Infinite Retrieval: Attention enhanced LLMs in long-context processing (arxiv.org)

26 points by TaurenHunter 1 year ago | 3 comments

Screenshot of arxiv.org: LM2: Large Memory Models

LM2: Large Memory Models (arxiv.org)

105 points by fzliu 1 year ago | 30 comments

Screenshot of arxiv.org: MemGPT: Towards LLMs as Operating Systems

MemGPT: Towards LLMs as Operating Systems (arxiv.org)

203 points by belter 3 years ago | 105 comments

Screenshot of arxiv.org: SparseLoCo: Communication-Efficient LLM Training

SparseLoCo: Communication-Efficient LLM Training (arxiv.org)

11 points by synapz_org 1 year ago | 1 comments

Screenshot of arxiv.org: LoRA Learns Less and Forgets Less

LoRA Learns Less and Forgets Less (arxiv.org)

169 points by wolecki 2 years ago | 59 comments

Looks similar

Lossless LLM compression for efficient GPU inference via dynamic-length float(arxiv.org)

Infinite Retrieval: Attention enhanced LLMs in long-context processing(arxiv.org)

LM2: Large Memory Models(arxiv.org)

MemGPT: Towards LLMs as Operating Systems(arxiv.org)

SparseLoCo: Communication-Efficient LLM Training(arxiv.org)

LoRA Learns Less and Forgets Less(arxiv.org)