Alistarh

d-alistarh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 2 papers 4 days ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published 5 days ago • 44

EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search

Paper • 2410.14649 • Published 22 days ago • 7

upvoted a paper 2 months ago

Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization

Paper • 2409.00492 • Published Aug 31 • 11

upvoted a collection 4 months ago

FP8 LLMs for vLLM

Collection

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated 24 days ago • 56

upvoted a collection 5 months ago

AQLM+PV

Collection

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 25 items • Updated 1 day ago • 18

upvoted a paper about 1 year ago

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Paper • 2203.07259 • Published Mar 14, 2022 • 3