Update README.md
Browse files
README.md
CHANGED
|
@@ -3,5 +3,5 @@ license: llama3.1
|
|
| 3 |
---
|
| 4 |
Amazingly quick to inference on Ada GPUs like 3090 Ti. in INT8. In VLLM I left it on a task for 10 minutes with prompt caching, average fixed input around 2000, variable input around 200 and output around 200.
|
| 5 |
Averaged over a second, that's 22.5k t/s prompt processing and 1.5k t/s generation.
|
| 6 |
-
Averaged over an hour that's 81M input tokens and 5.5M output tokens.
|
| 7 |
|
|
|
|
| 3 |
---
|
| 4 |
Amazingly quick to inference on Ada GPUs like 3090 Ti. in INT8. In VLLM I left it on a task for 10 minutes with prompt caching, average fixed input around 2000, variable input around 200 and output around 200.
|
| 5 |
Averaged over a second, that's 22.5k t/s prompt processing and 1.5k t/s generation.
|
| 6 |
+
Averaged over an hour that's 81M input tokens and 5.5M output tokens. Peak generation speed I see is around 2.6k/2.8k t/s.
|
| 7 |
|