End-to-end single-step decoding on DeepSeek-R1-Distill-LLaMA-8B 64K Context
24.1Latency (ms)
LessIsMore
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.08 | 24.1 | |
2025.08 | 24.8 | |
2025.08 | 25.4 | |
2025.08 | 34.4 |
LessIsMore
| Method | Links | |
|---|---|---|
2025.08 | 24.1 | |
2025.08 | 24.8 | |
2025.08 | 25.4 | |
2025.08 | 34.4 |