Time-to-first-token (TTFT) on Llama 8B Instruct 32K input length 3.1
3.4TTFT (s)
TriangleMix + FlexPrefill
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.07 | 3.4 | |
2025.07 | 3.5 | |
2025.07 | 3.6 | |
2025.07 | 3.6 | |
2025.07 | 3.6 | |
2025.07 | 4.1 | |
2025.07 | 4.1 | |
2025.07 | 4.2 | |
2025.07 | 5.5 |