Update benchmark scripts (#8)
This commit is contained in:
@@ -1,5 +1,7 @@
|
||||
## Run benchmark
|
||||
|
||||
NOTE: This is an implementation for replaying a given trace for throughput/latency benchmark purposes. It is not an actual ReAct agent implementation.
|
||||
|
||||
### Benchmark sglang
|
||||
```
|
||||
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
|
||||
|
||||
Reference in New Issue
Block a user