Scholar
Alexandre Marques
Google Scholar ID: p9zb2Y0AAAAJ
Neural Magic
deep learning
pruning
quantization
multi-fidelity analysis
embedded boundary
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
541
H-index
13
i10-index
17
Publications
20
Co-authors
0
Publications
5 items
H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache
2026
Cited
0
An Interpretable Latency Model for Speculative Decoding in LLM Serving
2026
Cited
0
Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption
2026
Cited
0
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
2025
Cited
0
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
arXiv.org · 2024
Cited
0
