Vladimir's picture

2 6 2

Vladimir

galqiwi

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

upvoted a paper 3 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

upvoted an article 4 months ago

Digest of models based on YandexGPT 5 Lite

View all activity

Organizations

upvoted a paper about 1 month ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 76

upvoted a paper 3 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8 • 110

upvoted an article 4 months ago

Article

Digest of models based on YandexGPT 5 Lite

By

•

Mar 19

• 31

upvoted 2 papers 5 months ago

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

Paper • 2501.02625 • Published Jan 5 • 16

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Paper • 2502.05003 • Published Feb 7 • 44

upvoted a collection 10 months ago

AQLM+PV

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 26 items • Updated Feb 28 • 21