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 17, 04:15 UTC
[Fix] Fissertion on YaRN model len (#2984)
Woosuk Kwon committed
Feb 23, 2024 at 12:57 UTC
f7c1234990793008f3d44790fd274040f26c4ee4
1 file changed
-1
vllm/model_executor/layers/rotary_embedding.py
-1
@@ -354,7 +354,6 @@ def get_rope(
354
elif scaling_type == "yarn":
355
original_max_position = rope_scaling[
356
"original_max_position_embeddings"]
357
- assert max_position == original_max_position * scaling_factor
357
extra_kwargs = {
358
k: v
359
for k, v in rope_scaling.items()