Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
<!-- TODO: add the upstream model's `license:` value to the frontmatter above before publishing. -->
|
| 5 |
|
|
@@ -179,4 +185,4 @@ to reproduce it:
|
|
| 179 |
| ITL p99 (ms) | 738.9 | 1079.2 |
|
| 180 |
| E2E median (ms) | 110457 | 85579 |
|
| 181 |
| KV cache peak | 100% | 100% |
|
| 182 |
-
| Duration (s) | 342.1 | 143.3 |
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- vllm
|
| 5 |
+
- inference-optimization
|
| 6 |
+
- benchmarking
|
| 7 |
+
- moe
|
| 8 |
+
- rocm
|
| 9 |
---
|
| 10 |
<!-- TODO: add the upstream model's `license:` value to the frontmatter above before publishing. -->
|
| 11 |
|
|
|
|
| 185 |
| ITL p99 (ms) | 738.9 | 1079.2 |
|
| 186 |
| E2E median (ms) | 110457 | 85579 |
|
| 187 |
| KV cache peak | 100% | 100% |
|
| 188 |
+
| Duration (s) | 342.1 | 143.3 |
|