Update README.md
Browse files
README.md
CHANGED
|
@@ -313,7 +313,12 @@ VLLM_DISABLE_COMPILE_CACHE=1 python benchmarks/benchmark_latency.py --input-len
|
|
| 313 |
|
| 314 |
We benchmarked the throughput in a serving environment.
|
| 315 |
|
| 316 |
-
Download sharegpt dataset:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 317 |
|
| 318 |
|
| 319 |
Other datasets can be found in: https://github.com/vllm-project/vllm/tree/main/benchmarks
|
|
|
|
| 313 |
|
| 314 |
We benchmarked the throughput in a serving environment.
|
| 315 |
|
| 316 |
+
Download sharegpt dataset:
|
| 317 |
+
|
| 318 |
+
```Shell
|
| 319 |
+
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
|
| 320 |
+
```
|
| 321 |
+
|
| 322 |
|
| 323 |
|
| 324 |
Other datasets can be found in: https://github.com/vllm-project/vllm/tree/main/benchmarks
|