Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM

First screen, captured 4 months ago.

Looks similar

Screenshot of arxiv.org: Accelerated AI Inference via Dynamic Execution Methods

Accelerated AI Inference via Dynamic Execution Methods (arxiv.org)

60 points by PaulHoule 1 year ago | 2 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: Matrix-vector multiplication implemented in off-the-shelf DRAM for Low-Bit LLMs

Matrix-vector multiplication implemented in off-the-shelf DRAM for Low-Bit LLMs (arxiv.org)

193 points by cpldcpu 1 year ago | 46 comments

Screenshot of arxiv.org: MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU

MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU (arxiv.org)

313 points by chrsw 6 months ago | 55 comments

Screenshot of arxiv.org: Every Flop Counts: Scaling a 300B LLM Without Premium GPUs

Every Flop Counts: Scaling a 300B LLM Without Premium GPUs (arxiv.org)

100 points by bretpiatt 1 year ago | 4 comments

Screenshot of arxiv.org: QLoRA: Efficient Finetuning of Quantized LLMs

QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org)

270 points by Garcia98 3 years ago | 90 comments