Fix inference container #135
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
IamGianluca
reviewed
Mar 9, 2022
docker/inference/dockerfile.ctr
Outdated
Comment on lines
57
to
67
| # Triton Server | ||
| FROM ${FULL_IMAGE} as full | ||
| WORKDIR /opt/tritonserver | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/LICENSE . | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/TRITON_VERSION . | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/NVIDIA_Deep_Learning_Container_License.pdf . | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/bin bin/ | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/lib lib/ | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/include include/ | ||
| COPY --chown=1000:1000 --from=full /opt/tritonserver/repoagents/ repoagents/ | ||
| COPY --chown=1000:1000 --from=full /usr/bin/serve /usr/bin/. |
There was a problem hiding this comment.
I think we will need to add these lines also in dockerfile.torch.
There was a problem hiding this comment.
@IamGianluca Triton server is already installed in pytorch and tensorflow inference containers
albertoa@pursuit-dgxstation:~/Projects/Merlin/docker/inference$ docker run --pull always --gpus=all -it --ipc=host --cap-add SYS_NICE nvcr.io/nvstaging/merlin/merlin-pytorch-inference:22.03 /bin/bash
22.03: Pulling from nvstaging/merlin/merlin-pytorch-inference
Digest: sha256:8be045dfbb42ea128aca833b78f4847bcc69557ba97f5e65a3703f50606fc646
Status: Image is up to date for nvcr.io/nvstaging/merlin/merlin-pytorch-inference:22.03
=============================
== Triton Inference Server ==
=============================
NVIDIA Release 22.02 (build 32400308)
Copyright (c) 2018-2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Various files include modifications (c) NVIDIA CORPORATION. All rights reserved.
This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
NOTE: Legacy NVIDIA Driver detected. Compatibility mode ENABLED.
root@3f045a14f399:/opt/tritonserver# ls -la
total 12396
drwxr-xr-x 1 root root 4096 Mar 4 10:17 .
drwxr-xr-x 1 root root 4096 Feb 18 05:47 ..
-rw-rw-r-- 1 triton-server triton-server 1485 Feb 18 01:23 LICENSE
-rw-rw-r-- 1 triton-server triton-server 3012640 Feb 18 01:23 NVIDIA_Deep_Learning_Container_License.pdf
-rw-rw-r-- 1 triton-server triton-server 7 Feb 18 01:23 TRITON_VERSION
drwxr-xr-x 1 triton-server triton-server 4096 Mar 4 10:17 backends
drwxr-xr-x 2 triton-server triton-server 4096 Feb 18 05:47 bin
drwxrwxr-x 15 root root 4096 Mar 4 08:20 cmake-3.21.1
-rw-r--r-- 1 root root 9629567 Jul 27 2021 cmake-3.21.1.tar.gz
drwxr-xr-x 3 triton-server triton-server 4096 Feb 18 05:47 include
drwxr-xr-x 2 triton-server triton-server 4096 Feb 18 05:47 lib
-rwxrwxr-x 1 triton-server triton-server 4266 Feb 18 05:41 nvidia_entrypoint.sh
drwxr-xr-x 1 triton-server triton-server 4096 Feb 18 05:48 repoagents
root@3f045a14f399:/opt/tritonserver# ls -la bin/
total 10848
drwxr-xr-x 2 triton-server triton-server 4096 Feb 18 05:47 .
drwxr-xr-x 1 root root 4096 Mar 4 10:17 ..
-rwxr-xr-x 1 triton-server triton-server 11092616 Feb 18 01:38 tritonserver
root@3f045a14f399:/opt/tritonserver#
This problems only happens in ctr (hugectr) since the base image is very minimal. I was working in getting smaller inference container since size was a problem for cloud providers, and I cut too much.
There was a problem hiding this comment.
Got it! Thank you for the explanation @albert17 👍
added 3 commits
March 9, 2022 13:43
This was
linked to
issues
Mar 10, 2022
jperez999
approved these changes
Mar 13, 2022
|
@albert17 ,when this PR can be merged, because inference-related CI of HugeCTR backend has failed to pass using old container |
|
merling-pytorch-inference and merlin-tensorflow-inference nightly are pushed |
|
@albert17 did you add FIL to both tensorflow-inference and pytorch-inference nightly containers? |
|
@IamGianluca Please try |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.