Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling Paper • 2609.36529 • Published 23 days ago • 39
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published about 1 month ago • 93
One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training Paper • 2609.11936 • Published Jul 2
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms Paper • 2609.38121 • Published 23 days ago • 28
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms Paper • 2609.38121 • Published 23 days ago • 28
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published about 1 month ago • 93
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization Paper • 2509.23202 • Published Sep 27, 2025 • 31
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments Paper • 2509.14233 • Published Sep 17, 2025 • 25
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published about 1 month ago • 93