Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Latency Speedup on SQuAD 2.0 (Question Answering)
Loading...
12.94
Throughput (TPS)
CreditDecoding
1.1568
4.2159
7.275
10.3341
Oct 7, 2025
Throughput (TPS)
Latency Speedup
Speedup vs Baseline (%)
Speedup vs Fast-dLLM (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Throughput (TPS)
Latency Speedup
Speedup vs Baseline (%)
Speedup vs Fast-dLLM (%)
CreditDecoding
Backbone=LLaDA-8B-Inst...
2025.10
12.94
-
706
22.4
Fast-dLLM
Backbone=LLaDA-8B-Inst...
2025.10
10.57
-
-
-
Baseline
Backbone=LLaDA-8B-Inst...
2025.10
1.61
-
-
-
Fast Post-Training Pruning Framework
Batch size=32, Backbon...
2022.03
-
1.37
-
-
Fast Post-Training Pruning Framework
Batch size=256, Backbo...
2022.03
-
1.4
-
-
Feedback
Search any
task
Search any
task