Attn-QAT: 4-Bit Attention With Quantization-Aware Training
Paper • 2603.00040 • Published • 3
lu hao
luhao1
·
AI & ML interests
None yet
Recent Activity
liked a model about 22 hours ago
mlx-community/Muse-Glimmer-30B-OptiQ-4bit liked a model 4 days ago
orcarouter/Qwen3.8-27B-Uncensored-FP8 liked a model 10 days ago
skibare87/gemma-4-12B-it-FP8-DSparkOrganizations
upvoted a paper about 2 months ago