Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Inference Efficiency on Efficient Qwen Competition Scenarios (Short/Medium/Long)

6.978Average Speedup

AFM-k5984d3s (Ours)

0.760882.374943.9895.60306Jul 5, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
6.9782327822,313
2026.07
12,5825,4416,576