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 15, 21:00 UTC
[Doc] Fix a typo (#14385)
Daniel Li committed
Mar 6, 2025 at 16:31 UTC
ad60bbb2b22f532bdb201ae8ab91c1a3d001c243
1 file changed
+1
-1
benchmarks/benchmark_serving.py
+1
-1
@@ -174,7 +174,7 @@ def sample_sonnet_requests(
174
) -> list[tuple[str, str, int, int, None]]:
175
assert (
176
input_len > prefix_len
177
- ), "'args.sonnet-input-len' must be greater than 'args.prefix-input-len'."
177
+ ), "'args.sonnet-input-len' must be greater than 'args.sonnet-prefix-len'."
178
179
# Load the dataset.
180
with open(dataset_path, encoding='utf-8') as f: