Update README.md
Browse files
README.md
CHANGED
|
@@ -166,7 +166,7 @@ vllm serve "${MODEL}" \
|
|
| 166 |
|
| 167 |
## Performance
|
| 168 |
|
| 169 |
-
On dual RTX Pro 6000, I can reach over 5.5k prefill/prompt/context processing and over 100 tok/s.
|
| 170 |
|
| 171 |
|
| 172 |
|
|
|
|
| 166 |
|
| 167 |
## Performance
|
| 168 |
|
| 169 |
+
On dual RTX Pro 6000, I can reach over 5.5k prefill/prompt/context processing and over 100 tok/s token generation for a single request.
|
| 170 |
|
| 171 |
|
| 172 |
|