YuyangXie
YuyangXie
ยท
AI & ML interests
Edge LLM, quantization, Speculative decoding, inference
Recent Activity
upvoted
an
article
6 days ago
The Optimal Architecture for Small Language Models
liked
a model
13 days ago
zai-org/GLM-4.7
upvoted
a
paper
2 months ago
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization
Formats
Organizations
None yet