MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
Paper
•
2602.03537
•
Published
•
2
Max Kleinegger
mkleinegger
·
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
upvoted
a
paper
3 days ago
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
upvoted
a
paper
3 days ago
Bridging the Gap Between Promise and Performance for Microscaling FP4
Quantization
Organizations
authored
a
paper
3 days ago