ClearML/clearml-agent
1
0
Fork 0
mirror of https://github.com/clearml/clearml-agent synced 2025-03-03 10:42:05 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix torch inside nvidia containers to use preinstalled version (i.e. ==x.y.z.* matching)

Browse Source
This commit is contained in:
allegroai 2023-03-05 17:59:57 +02:00
parent 3cedc104df
commit bfc4ba38cd
2 changed files with 52 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
clearml_agent/backend_api/config/default/agent.conf
View File

@ -341,4 +341,47 @@
# and arguments specified in the task's container section (setup shell script from the task container section will
# be used in any case, if specified).
disable_task_docker_override: false
# Choose the default docker based on the Task properties,
# Examples: 'script.requirements', 'script.binary', 'script.repository', 'script.branch', 'project'
# Notice: Matching is done via regular expression, for example "^searchme$" will match exactly "searchme$" string
#
# "default_docker": {
# "image": "nvidia/cuda:10.2-cudnn7-runtime-ubuntu18.04",
# # optional arguments to pass to docker image
# # arguments: ["--ipc=host", ]
# "match_rules": [
# {
# "image": "sample_container:tag",
# "arguments": "-e VALUE=1 --ipc=host",
# "match": {
# "script": {
# "requirements": {
# "pip": {
# "tensorflow": "~=1.6"
# }
# },
# "repository": "",
# "branch": "master"
# },
# "project": "example"
# }
# },
# {
# "image": "better_container:tag",
# "arguments": "",
# "match": {
# "container": "replace_me_please"
# }
# },
# {
# "image": "another_container:tag",
# "arguments": "",
# "match": {
# "project": "^examples", # anything that starts with "examples", e.g. "examples", "examples/sub_project"
# }
# }
# ]
# },
#
}

10
clearml_agent/helper/package/pytorch.py
View File

@ -493,7 +493,15 @@ class PytorchRequirement(SimpleSubstitution):
if req.specs and len(req.specs) == 1 and req.specs[0][0] == "==":
# remove any +cu extension and let pip resolve that
line = "{} {}".format(req.name, req.format_specs(max_num_parts=3))
# and add .* if we have 3 parts version to deal with nvidia container 'a' version
# i.e. "1.13.0" -> "1.13.0.*" so it should match preinstalled "1.13.0a0+936e930"
spec_3_parts = req.format_specs(num_parts=3)
spec_max3_parts = req.format_specs(max_num_parts=3)
if spec_3_parts == spec_max3_parts and not spec_max3_parts.endswith("*"):
line = "{} {}.*".format(req.name, spec_max3_parts)
else:
line = "{} {}".format(req.name, spec_max3_parts)
if req.marker:
line += " ; {}".format(req.marker)
else: