Dan Alistarh

Dan Alistarh on Hugging Face Daily Papers: 7 papers, 3 in the top 3 of their day, 303 upvotes.

1. Quartet: Native FP4 Training Can Be Optimal for Large Language Models 73 upvotes, #4 of 2025-05-26
2. Hogwild! Inference: Parallel LLM Generation via Concurrent Attention 98 upvotes, #2 of 2025-04-09
3. "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization 44 upvotes, #2 of 2024-11-05
4. EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search 6 upvotes, #10 of 2024-10-23
5. Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization 10 upvotes, #12 of 2024-09-04
6. QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models 27 upvotes, #4 of 2023-10-26
7. Scaling Laws for Sparsely-Connected Foundation Models 15 upvotes, #3 of 2023-09-18

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.