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, 16:00 UTC
Update BASE_IMAGE to 2.22 release of Neuron (#16218)
Satyajith Chilappagari committed
Apr 7, 2025 at 19:11 UTC
1d01211264cd58e287a3d09c3980d367a53bc9cf
1 file changed
+4
-4
docker/Dockerfile.neuron
+4
-4
@@ -1,6 +1,6 @@
1
# default base image
2
# https://gallery.ecr.aws/neuron/pytorch-inference-neuronx
3
-ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.5.1-neuronx-py310-sdk2.21.0-ubuntu22.04"
3
+ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.5.1-neuronx-py310-sdk2.22.0-ubuntu22.04"
4
5
FROM $BASE_IMAGE
6
@@ -21,9 +21,9 @@ VOLUME [ ${APP_MOUNT} ]
21
WORKDIR ${APP_MOUNT}/vllm
22
23
RUN python3 -m pip install --upgrade pip
24
-RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas
25
-RUN python3 -m pip install sentencepiece transformers==4.45.2 -U
26
-RUN python3 -m pip install neuronx-cc==2.16.345.0 --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
24
+RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas tenacity
25
+RUN python3 -m pip install sentencepiece transformers==4.48.0 -U
26
+RUN python3 -m pip install neuronx-cc==2.17.194.0 --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
27
RUN python3 -m pip install pytest
28
29
# uninstall transformers-neuronx package explicitly to avoid version conflict