Flux Attention uses a context-aware Layer Router to dynamically assign full or sparse attention to each LLM layer, achieving up to 2.8x prefill and 2.0x decode speedups with competitive performance on long-context and reasoning tasks.
Efficient context scaling with longcat zigzag attention
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
SnapMLA achieves up to 1.91x higher throughput in long-output MLA decoding using FP8 quantization and specialized kernels while keeping benchmark quality near the BF16 baseline.
citing papers explorer
-
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
Flux Attention uses a context-aware Layer Router to dynamically assign full or sparse attention to each LLM layer, achieving up to 2.8x prefill and 2.0x decode speedups with competitive performance on long-context and reasoning tasks.
-
SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
SnapMLA achieves up to 1.91x higher throughput in long-output MLA decoding using FP8 quantization and specialized kernels while keeping benchmark quality near the BF16 baseline.