mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: More GPU results and improvements in the example docs (#2674)

Browse Source 
* add more results and improve the example docs

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* 5070 windows timing

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add reference for cpu-only

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-11-24 15:26:08 +01:00
committed by GitHub
parent 146b4f0535
commit b75c6461f4
3 changed files with 79 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
docs/usage/gpu.md vendored
View File

@@ -126,18 +126,38 @@ TBA.
## Performance results
Test data:
- Number of pages: 192
- Number of tables: 95
### Test data
Test infrastructure:
- Instance type: `g6e.2xlarge`
- CPU: 8 vCPUs, AMD EPYC 7R13
- RAM: 64GB
- GPU: NVIDIA L40S 48GB
- CUDA Version: 13.0, Driver Version: 580.95.05
| | PDF doc | [ViDoRe V3 HR](https://huggingface.co/datasets/vidore/vidore_v3_hr) |
| - | - | - |
| Num docs | 1 | 14 |
| Num pages | 192 | 1110 |
| Num tables | 95 | 258 |
| Format type | PDF | Parquet of images |
| Pipeline | Page efficiency |
| - | - |
| Standard - Inline | 3.1 pages/second |
| VLM - Inference server (GraniteDocling) | 2.4 pages/second |
### Test infrastructure
| | g6e.2xlarge | RTX 5090 | RTX 5070 |
| - | - | - | - |
| Description | AWS instance `g6e.2xlarge` | Linux bare metal machine | Windows 11 bare metal machine |
| CPU | 8 vCPUs, AMD EPYC 7R13 | 16 vCPU, AMD Ryzen 7 9800 | 16 vCPU, AMD Ryzen 7 9800 |
| RAM | 64GB | 128GB | 64GB |
| GPU | NVIDIA L40S 48GB | NVIDIA GeForce RTX 5090 | NVIDIA GeForce RTX 5070 |
| CUDA Version | 13.0, driver 580.95.05 | 13.0, driver 580.105.08 | 13.0, driver 581.57 |
### Results
<table>
<thead>
<tr><th rowspan="2">Pipeline</th><th colspan="2">g6e.2xlarge</th><th colspan="2">RTX 5090</th><th colspan="2">RTX 5070</th></tr>
<tr><th>PDF doc</th><th>ViDoRe V3 HR</th><th>PDF doc</th><th>ViDoRe V3 HR</th><th>PDF doc</th><th>ViDoRe V3 HR</th></tr>
</thead>
<tbody>
<tr><td>Standard - Inline (no OCR)</td><td>3.1 pages/second</td><td>-</td><td>7.9 pages/second<br /><small><em>[cpu-only]* 1.5 pages/second</em></small></td><td>-</td><td>4.2 pages/second<br /><small><em>[cpu-only]* 1.2 pages/second</em></small></td><td>-</td></tr>
<tr><td>VLM - Inference server (GraniteDocling)</td><td>2.4 pages/second</td><td>-</td><td>3.8 pages/second</td><td>3.6-4.5 pages/second</td><td>-</td><td>-</td></tr>
</tbody>
</table>
_* cpu-only timing computed with 16 pytorch threads._