Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -39,11 +39,11 @@ Endpoints: the standard decision protocols `POST /v1/systemone` and `POST /v1/de
|
|
| 39 |
|
| 40 |
Measured on one RTX 4090, end to end over HTTP, against the model author's own server (`von serve`). A ratio above 1x means Verdict is ahead.
|
| 41 |
|
| 42 |
-
| concurrency | Verdict
|
| 43 |
|---|---:|---:|---:|---:|---:|---:|
|
| 44 |
-
| 1 | 113.8 | 46.4 | 2.45x | 8.61
|
| 45 |
-
| 8 | 536.4 | 31.2 | 17.2x | 14.86
|
| 46 |
-
| 64 | 1476.1 | 22.3 | 66.1x | 42.58
|
| 47 |
|
| 48 |
## Files
|
| 49 |
|
|
|
|
| 39 |
|
| 40 |
Measured on one RTX 4090, end to end over HTTP, against the model author's own server (`von serve`). A ratio above 1x means Verdict is ahead.
|
| 41 |
|
| 42 |
+
| concurrency | Verdict rps | `von serve` rps | rps ratio | Verdict P50 / P99 (ms) | `von serve` P50 / P99 (ms) | P50 / P99 ratio |
|
| 43 |
|---|---:|---:|---:|---:|---:|---:|
|
| 44 |
+
| 1 | 113.8 | 46.4 | 2.45x | 8.61 / 11.98 | 22.89 / 28.46 | 2.66 / 2.38x |
|
| 45 |
+
| 8 | 536.4 | 31.2 | 17.2x | 14.86 / 16.61 | 250.91 / 435.99 | 16.9 / 26.2x |
|
| 46 |
+
| 64 | 1476.1 | 22.3 | 66.1x | 42.58 / 53.24 | 2848.80 / 3333.40 | 66.9 / 62.6x |
|
| 47 |
|
| 48 |
## Files
|
| 49 |
|