Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection Paper • 2609.35932 • Published 24 days ago • 8 • 7
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Paper • 2511.14102 • Published 2 days ago • 19 • 2
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning Paper • 2610.26754 • Published 3 days ago • 2 • 3
guicybercode/Aira-2-portuguese-124M-mlx-4bit Text Generation • 0.1B • Updated about 24 hours ago • 13
guicybercode/Aira-2-portuguese-124M-mlx-4bit Text Generation • 0.1B • Updated about 24 hours ago • 13