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, 23:15 UTC
[CI/Build] Fix Args for `_get_logits_warper` in Sampler Test (#5922)
Roger Wang committed
Jun 27, 2024 at 11:43 UTC
736ed388492c5c10deb7522637a94c041f163f48
1 file changed
+1
-1
tests/samplers/test_sampler.py
+1
-1
@@ -587,7 +587,7 @@ def test_sampler_top_k_top_p(seed: int, device: str):
587
generation_config = GenerationConfig(top_k=top_k,
588
top_p=top_p,
589
do_sample=True)
590
- warpers = generation_model._get_logits_warper(generation_config)
590
+ warpers = generation_model._get_logits_warper(generation_config, device)
591
assert len(warpers) == 2 # top_p and top_k
592
593
seq_group_metadata_list: List[SequenceGroupMetadata] = []