A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 06:45 UTC
[Minor] Fix comment (#1704)
Zhuofan committed
Nov 18, 2023 at 01:42 UTC
dcc543a298f0e3af670f329367ba13cd07f68342
1 file changed
+1
-1
benchmarks/benchmark_throughput.py
+1
-1
@@ -100,7 +100,7 @@ def run_vllm(
100
)
101
102
start = time.perf_counter()
103
- # FIXME(woosuk): Do use internal method.
103
+ # FIXME(woosuk): Do not use internal method.
104
llm._run_engine(use_tqdm=True)
105
end = time.perf_counter()
106
return end - start