Benchmark Updates (#382)

benchmark/multi_chain_reasoning/README.md

@@ -7,7 +7,7 @@ wget https://raw.githubusercontent.com/openai/grade-school-math/master/grade_sch
 
 ### Benchmark sglang
 ```
-python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
+python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000  --schedule-conservativeness 1.3
 ```
 
 ```

benchmark/multi_chain_reasoning/bench_sglang.py

@@ -86,7 +86,7 @@ def main(args):
     # Run requests
     tic = time.time()
     states = multi_chain_gsm8k.run_batch(
-        arguments, temperature=0, backend=backend, num_threads=args.parallel)
+        arguments, temperature=0, backend=backend, num_threads=args.parallel, progress_bar=True)
     latency = time.time() - tic
 
     preds = []