Dan Alistarh

dalistarh's activity

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

authored a paper about 1 month ago

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

Paper • 2505.14669 • Published May 20 • 76

authored a paper 3 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8 • 110

authored a paper 8 months ago

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

Paper • 2411.02355 • Published Nov 4, 2024 • 52

authored a paper 9 months ago

EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search

Paper • 2410.14649 • Published Oct 18, 2024 • 9

authored a paper 10 months ago

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

Paper • 2409.00492 • Published Aug 31, 2024 • 11

authored 2 papers over 1 year ago

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Paper • 2210.17323 • Published Oct 31, 2022 • 8

QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

Paper • 2310.16795 • Published Oct 25, 2023 • 27

authored a paper almost 2 years ago

Scaling Laws for Sparsely-Connected Foundation Models

Paper • 2309.08520 • Published Sep 15, 2023 • 13