)))?!?((('s picture

)))?!?(((

stereoplegic

·

AI & ML interests

None yet

Recent Activity

new activity about 2 months ago

OpenNLPLab/TransNormerLLM-7B:Unsafe use of eval

updated a model about 2 months ago

ScienceArtMagic/QWERTY

updated a collection 4 months ago

View all activity

Organizations

stereoplegic's activity

New activity in OpenNLPLab/TransNormerLLM-7B about 2 months ago

Unsafe use of eval

#1 opened about 1 year ago by

Daniel-P-Gonzalez

updated a model about 2 months ago

ScienceArtMagic/QWERTY

Text Generation • Updated Nov 30, 2024 • 1

updated a collection 4 months ago

Coding

193 items • Updated Oct 4, 2024 • 19

commented 2 papers 4 months ago

CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs

Paper • 2409.12490 • Published Sep 19, 2024 •

Inference-Friendly Models With MixAttention

Paper • 2409.15012 • Published Sep 23, 2024 •

updated 3 collections 4 months ago

Attention

127 items • Updated Sep 30, 2024 • 4

KV Cache

18 items • Updated Sep 30, 2024 • 3

Long context

94 items • Updated Sep 29, 2024 • 30

commented 2 papers 4 months ago

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

Paper • 2406.19707 • Published Jun 28, 2024 •

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding

Paper • 2409.08561 • Published Sep 13, 2024 •

updated 2 collections 4 months ago

CoT

100 items • Updated Sep 26, 2024 • 8

Long context

94 items • Updated Sep 29, 2024 • 30

commented 2 papers 4 months ago

Diver: Large Language Model Decoding with Span-Level Mutual Information Verification

Paper • 2406.02120 • Published Jun 4, 2024 •

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

Paper • 2405.07542 • Published May 13, 2024 •

updated a collection 4 months ago

Speculative

60 items • Updated Sep 24, 2024 • 5

commented a paper 4 months ago

PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation

Paper • 2407.11798 • Published Jul 16, 2024 • 1 •

updated a collection 4 months ago

Speculative

60 items • Updated Sep 24, 2024 • 5

commented a paper 4 months ago

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Paper • 2408.08696 • Published Aug 16, 2024 •

updated a collection 4 months ago

Speculative

60 items • Updated Sep 24, 2024 • 5