Update README.md
Browse files
README.md
CHANGED
|
@@ -332,7 +332,7 @@ python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --
|
|
| 332 |
### int4wo-hqq
|
| 333 |
Server:
|
| 334 |
```Shell
|
| 335 |
-
vllm serve pytorch/Phi-4-mini-instruct-int4wo-hqq --tokenizer microsoft/Phi-4-mini-instruct -O3 --pt-load-map-location cuda:0
|
| 336 |
```
|
| 337 |
|
| 338 |
Client:
|
|
|
|
| 332 |
### int4wo-hqq
|
| 333 |
Server:
|
| 334 |
```Shell
|
| 335 |
+
VLLM_DISABLE_COMPILE_CACHE=1 vllm serve pytorch/Phi-4-mini-instruct-int4wo-hqq --tokenizer microsoft/Phi-4-mini-instruct -O3 --pt-load-map-location cuda:0
|
| 336 |
```
|
| 337 |
|
| 338 |
Client:
|