LLM Training on Qwen2.5-7B 256K context (train)
1,301.6Throughput (tokens/sec)
OOMB (Sparse Attn)
Updated 3d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 1,301.6 | |
2026.02 | 1,265.59 | |
2026.02 | 266.13 | |
2026.02 | 261.47 | |
2026.02 | 218.41 | |
2026.02 | 50 | |
2026.02 | 49 |
OOMB (Sparse Attn)
| Method | Links | |
|---|---|---|
2026.02 | 1,301.6 | |
2026.02 | 1,265.59 | |
2026.02 | 266.13 | |
2026.02 | 261.47 | |
2026.02 | 218.41 | |
2026.02 | 50 | |
2026.02 | 49 |