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, 05:45 UTC
[Neuron] Upgrade neuron to 2.20.2 (#11016)
Signed-off-by: Jerzy Zagorski <jzagorsk@amazon.com> Co-authored-by: Jerzy Zagorski <jzagorsk@amazon.com>
xendo committed
Dec 9, 2024 at 22:53 UTC
9c6459e4cb020ec1ad9ea08cac9309b83d432fc8
2 files changed
+3
-2
Dockerfile.neuron
+2
-1
@@ -1,5 +1,6 @@
1
# default base image
2
-ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.1.2-neuronx-py310-sdk2.20.0-ubuntu20.04"
2
+# https://gallery.ecr.aws/neuron/pytorch-inference-neuronx
3
+ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.1.2-neuronx-py310-sdk2.20.2-ubuntu20.04"
4
5
FROM $BASE_IMAGE
6
vllm/utils.py
+1
-1
@@ -1628,7 +1628,7 @@ def direct_register_custom_op(
1628
library object. If you want to bind the operator to a different library,
1629
make sure the library object is alive when the operator is used.
1630
"""
1631
- if is_in_doc_build():
1631
+ if is_in_doc_build() or not supports_custom_op():
1632
return
1633
import torch.library
1634
if hasattr(torch.library, "infer_schema"):