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, 13:30 UTC
[Minor] Fix lint error in main branch (#17233)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Apr 26, 2025 at 11:10 UTC
43eea2953ba23b80cc174bd24c9ce4886e6459f3
1 file changed
+2
-2
vllm/model_executor/layers/rotary_embedding.py
+2
-2
@@ -1329,8 +1329,8 @@ class MRotaryEmbedding(RotaryEmbedding):
1329
audio_llm_pos_ids_list = (torch.arange(
1330
min(t_ntoken_per_chunk, pure_audio_len -
1331
added_audio_len)).expand(3, -1) +
1332
- audio_start_idx).split(
1333
- 1, dim=1)
1332
+ audio_start_idx).split(1,
1333
+ dim=1)
1334
else:
1335
audio_llm_pos_ids_list = []
1336
added_audio_len += min(t_ntoken_per_chunk,