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, 04:45 UTC
[Benchmark][Bugfix] Fix Dataset Length Calculation (#19868)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Jun 19, 2025 at 21:30 UTC
10d82f9ac5bd83861f0265e3f30e90ca8ff2cf63
1 file changed
+1
-1
benchmarks/benchmark_dataset.py
+1
-1
@@ -353,7 +353,7 @@ class RandomDataset(BenchmarkDataset):
353
: input_lens[i]
354
]
355
prompt = tokenizer.decode(re_encoded_sequence)
356
- total_input_len = prefix_len + int(input_lens[i])
356
+ total_input_len = len(re_encoded_sequence)
357
requests.append(
358
SampleRequest(
359
prompt=prompt,