Tomer Ronen's picture

3

Tomer Ronen

tomer-nv

·

AI & ML interests

None yet

Recent Activity

authored a paper 16 days ago

FFN Fusion: Rethinking Sequential Computation in Large Language Models

authored a paper 4 months ago

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

new activity 6 months ago

nvidia/Llama-3_1-Nemotron-51B-Instruct:Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model

View all activity

Organizations

tomer-nv's activity

New activity in nvidia/Llama-3_1-Nemotron-51B-Instruct 6 months ago

Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model

#19 opened 6 months ago by

Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model

#18 opened 6 months ago by

fixed cache over-alloc bug

#17 opened 6 months ago by