Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
Paper • 2604.07394 • Published • 16
Flux Attention
🚀 Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
-
-
QQTang1223/full_streaming_Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 282 -
QQTang1223/full_xattn_Qwen3-8B
Text Generation • 8B • Updated • 289 • 1 -
QQTang1223/full_xattn_Qwen3-4B
Text Generation • 4B • Updated • 278 -
QQTang1223/full_xattn_Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 284 -
QQTang1223/full_triangle_Qwen3-8B
Text Generation • 8B • Updated • 297 -
QQTang1223/full_triangle_Qwen3-4B
Text Generation • 4B • Updated • 307 -
QQTang1223/full_triangle_Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 317 -
QQTang1223/full_streaming_Qwen3-8B
Text Generation • 8B • Updated • 271 -
QQTang1223/full_streaming_Qwen3-4B
Text Generation • 4B • Updated • 316 -
QQTang1223/qwen_mix_sft_64K6
Viewer • Updated • 49.3k • 32 -
QQTang1223/llama_mix_sft_64K6
Viewer • Updated • 49.3k • 32 -
QQTang1223/xattn_streaming_Qwen3-4B
Text Generation • 4B • Updated • 232