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 4, 13:45 UTC
Bugfix: fix SpecBench sample argument error (#40927)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
zhrrr committed
Apr 28, 2026 at 15:33 UTC
ea74f701db6c0dd4b2d954f5e79841101d0d8a5d
1 file changed
+1
vllm/benchmarks/datasets/datasets.py
+1
@@ -2365,6 +2365,7 @@ class SpecBench(CustomDataset):
2365
random.shuffle(self.data)
2366
2367
def sample(
2368
+ self,
2369
**kwargs,
2370
) -> list[SampleRequest]:
2371
# leverage CustomDataset sample