Update README.md
Browse files
README.md
CHANGED
|
@@ -48,14 +48,14 @@ Thanks to its hybrid attention mechanism and highly sparse MoE architecture, `Ri
|
|
| 48 |
<div style="display: flex; justify-content: center; align-items: flex-start; gap: 20px;">
|
| 49 |
<div style="text-align: center;">
|
| 50 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/yHVE-nmTgV3w0z4X2eg_g.png" width="500">
|
| 51 |
-
<p style="margin-top: 8px; font-size: 14px;"><strong>Figure
|
| 52 |
</div>
|
| 53 |
|
| 54 |
<div style="text-align: center;">
|
| 55 |
<p align="center">
|
| 56 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/mTqsHh0yFtQjpCN_fw4e0.png" width="500">
|
| 57 |
</p>
|
| 58 |
-
<p style="margin-top: 8px; font-size: 14px;"><strong>Figure
|
| 59 |
</div>
|
| 60 |
|
| 61 |
</div>
|
|
|
|
| 48 |
<div style="display: flex; justify-content: center; align-items: flex-start; gap: 20px;">
|
| 49 |
<div style="text-align: center;">
|
| 50 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/yHVE-nmTgV3w0z4X2eg_g.png" width="500">
|
| 51 |
+
<p style="margin-top: 8px; font-size: 14px;"><strong>Figure 3:</strong> Ring-mini-linear-2.0 prefill throughput</p>
|
| 52 |
</div>
|
| 53 |
|
| 54 |
<div style="text-align: center;">
|
| 55 |
<p align="center">
|
| 56 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/mTqsHh0yFtQjpCN_fw4e0.png" width="500">
|
| 57 |
</p>
|
| 58 |
+
<p style="margin-top: 8px; font-size: 14px;"><strong>Figure 4:</strong> Ring-mini-linear-2.0 decode throughput</p>
|
| 59 |
</div>
|
| 60 |
|
| 61 |
</div>
|