arxiv:2504.06261
Vage Egiazarian
Vahe527887
AI & ML interests
NLP, LLM compression
Recent Activity
upvoted
a
paper
11 days ago
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
authored
a paper
about 2 months ago
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
liked
a model
9 months ago
ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16
Organizations
None yet
