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 16, 15:45 UTC
[MISC] remove engine_use_ray in benchmark_throughput.py (#8615)
Kunshang Ji committed
Sep 19, 2024 at 13:33 UTC
855c8ae2c9a4085b1ebd66d9a978fb23f47f822c
1 file changed
-1
benchmarks/benchmark_throughput.py
-1
@@ -191,7 +191,6 @@ async def run_vllm_async(
191
use_v2_block_manager=use_v2_block_manager,
192
disable_async_output_proc=disable_async_output_proc,
193
worker_use_ray=False,
194
- engine_use_ray=False,
194
disable_log_requests=True,
195
)
196