Reza Yazdani Aminabadi
3 papers · 2022–2023 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(2)
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(13)
🧭
Keyword Pioneer
Conferences
ICML (2)
NIPS (1)
Top co-authors
Keywords
weight quantization
(2)
inference optimization
(2)
transformer model
(2)
model compression
(2)
model inference
(1)
training efficiency
(1)
sparse model
(1)
mixture of expert
(1)
latency optimization
(1)
activation quantization
(1)
large language model
(1)
int4 quantization
(1)
transformer architecture
(1)
post-training quantization
(1)
knowledge distillation
(1)
Papers
Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
ICML 2023
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
NIPS 2022
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
ICML 2022