We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 04c8147 commit 56766b2Copy full SHA for 56766b2
tensorrt_llm/bench/benchmark/low_latency.py
@@ -11,8 +11,8 @@
11
optgroup)
12
from huggingface_hub import snapshot_download
13
14
-from tensorrt_llm._tensorrt_engine import LLM
15
from tensorrt_llm import LLM as PyTorchLLM
+from tensorrt_llm._tensorrt_engine import LLM
16
from tensorrt_llm.bench.benchmark.utils.asynchronous import async_benchmark
17
from tensorrt_llm.bench.benchmark.utils.general import generate_warmup_dataset
18
from tensorrt_llm.bench.benchmark.utils.processes import IterationWriter
0 commit comments