allegroai
e43f31eb80
Version bump
2022-04-13 10:02:25 +03:00
allegroai
f50ba005b5
Protect dynamic GPUs from failing to parse worker GPU index
2022-04-13 10:01:50 +03:00
allegroai
1011544533
Fix copy breaks agent and nulls the worker name
2022-04-13 10:01:12 +03:00
allegroai
6572023173
Fix avoid reinstall pytorch package if the same version is already installed
2022-04-09 14:18:38 +03:00
allegroai
9c7e2aacd0
Fix PYTHONPATH is overwritten when executing a task (append to it instead)
2022-04-09 14:17:49 +03:00
allegroai
5446aed9cf
Version bump to v1.2.2
2022-03-30 20:48:28 +03:00
allegroai
b94ec85461
Fix update should run with -y
2022-03-30 20:48:11 +03:00
allegroai
f55f4f7535
Version bump
2022-03-30 20:11:13 +03:00
allegroai
c87da3a079
Fix apt-get update fail causes apt-get install to not be executed
2022-03-30 20:10:57 +03:00
allegroai
c3590a53a8
Fix CLEARML_AGENT_SKIP_PIP_VENV_INSTALL fails to find python executable
2022-03-30 20:10:08 +03:00
allegroai
a4315722ab
Version bump to vv1.2.1
2022-03-28 18:13:20 +03:00
allegroai
c901bd331c
Fix git packages are installed even if commit is given and is preinstalled when using cached virtual environment
2022-03-28 18:11:46 +03:00
allegroai
df97f170a2
Fix clearml-agent init
...
Use app.clear.ml as default server
Add git token refrences
2022-03-24 22:08:06 +02:00
allegroai
a30a2dad66
Add git personal token docs
2022-03-24 22:07:15 +02:00
allegroai
2432f5bb68
Add CLEARML_AGENT_PROPAGATE_EXITCODE, set to 1 to let clearml-agent execute retrun a nonzero exit code on failure (notice by default we keep the retrun code 0, the exception is the k8s glue with non-restarting Pods, where users would want to get visibility into failing Tasks, do not use unless you know what to expect from k8s)
2022-03-24 22:04:25 +02:00
allegroai
341086d86a
Fix vcs packages are reinstalled when same commit version is already installed
2022-03-24 22:03:25 +02:00
allegroai
1163c96438
Add agent.package_manager.force_original_requirements allowing to only use the "org_pip" coming from dev execution (using this prevents editing the installed packages from the UI)
2022-03-24 22:00:33 +02:00
allegroai
4c120d7cd0
Add ability to override container LOCAL_PYTHON, add auto python support (max 3.15)
2022-03-24 21:58:07 +02:00
allegroai
8712c5e636
Fix PyTorch aarch64 and windows support
2022-03-16 17:40:21 +02:00
allegroai
a51f9bed49
Version bump
2022-03-15 10:04:45 +02:00
allegroai
531e514003
Add custom build script support
...
Add extra configurations when starting daemon
Propagate token to docker in case credentials are not available
2022-03-15 10:04:25 +02:00
allegroai
2cd9e706c8
Fix user-provided " is unnecessarily replaced to \\"
2022-03-15 10:02:28 +02:00
Idan Tene
e3e6a1dda8
Fix virtualenv python interpreter used ( #98 )
...
* Add virtualenv version logging
* Force using requested python interpreter
2022-02-27 11:25:25 +02:00
pollfly
36073ad488
Fix links ( #100 )
2022-02-17 12:04:11 +02:00
allegroai
d89d0f9ff5
Fix pathlib2 six conflict, version bump
2022-02-09 18:29:04 +02:00
allegroai
14c48d0a78
Fix FORCE_LOCAL_CLEARML_AGENT_WHEEL when running from a Windows host
2022-02-09 18:28:17 +02:00
allegroai
b1ee3e105b
Version bump
2022-02-07 20:05:03 +02:00
allegroai
1f53c4fd1b
Fix agent fails to check out code from main branch when branch/commit is not explicitly specified
2022-02-07 20:04:08 +02:00
allegroai
bfed3ccf4d
Fix agent attempts to check out code when in standalone mode
2022-02-07 20:03:08 +02:00
pollfly
d521482409
Add spaces to help menu ( #96 )
2022-02-06 12:45:21 +02:00
allegroai
53eba5658f
Fix conda package manager listed packages with local links (@ file://) should ignore the local package if it does not exist
...
Fix cuda patch version support in conda
2022-02-02 16:33:07 +02:00
allegroai
bb64e4a850
Fix hide_docker_command_env_vars mode to include URL passwords and handle env vars containing docker commands
2022-02-02 16:30:34 +02:00
allegroai
771690d5c0
Fix ENV_API_DEFAULT_REQ_METHOD no default value causes ValueError if not specified
2022-01-31 12:39:39 +02:00
pollfly
d39e30995a
Fix links ( #93 )
2022-01-27 12:15:36 +02:00
allegroai
363aaeaba8
Fix symbolic links not copied from cached VCS into working copy. Windows platform will result with default copy content instead of original symbolic link (issue #89 )
2022-01-23 10:42:11 +02:00
allegroai
fa1307e62c
Add agent.poetry_version to specify poetry version (and force installation of poetry if missing)
2022-01-23 10:40:05 +02:00
allegroai
e7c9e9695b
Fix using deprecated abc support
2022-01-23 10:39:13 +02:00
Mal Miller
bf07b7f76d
Add environment variable for request method ( #91 )
...
* Add environment variable for default request method
2022-01-12 20:29:17 +02:00
allegroai
5afb604e3d
Fix default_python set to None
2022-01-07 15:12:27 +02:00
allegroai
b3e8be6296
Add agent.force_git_root_python_path configuration setting to force adding the git repository root folder to the PYTHONPATH (if set working directory is not added to the PYHTONPATH)
2022-01-07 15:11:59 +02:00
allegroai
2cb452b1c2
Version bump
2021-12-29 13:21:31 +02:00
allegroai
938fcc4530
Add build --force-docker command line argument to the to allow ignoring task container data
2021-12-29 13:21:25 +02:00
allegroai
73625bf00f
Version bump
2021-12-21 14:29:43 +02:00
allegroai
f41ed09dc1
Add support for custom docker image resolving
2021-12-21 14:29:43 +02:00
allegroai
f03c4576f7
Update default docker image
2021-12-21 14:29:43 +02:00
allegroai
5a6caf6399
Fix "git+git://" requirements
2021-10-29 22:58:28 +03:00
allegroai
a07053d961
Version bump to v1.1.1
2021-10-26 10:12:21 +03:00
allegroai
aa9a9a25fb
version bump
2021-10-21 12:03:29 +03:00
allegroai
cd4a39d8fc
Fix config example
2021-10-21 12:03:07 +03:00
allegroai
92e3f00435
Add support for truncating task log file after reporting to server
2021-10-21 12:02:31 +03:00
allegroai
a890e36a36
Fix PY2.7 support for pytorch
2021-10-19 10:47:09 +03:00
allegroai
bed94ee431
Add support for configuration env and files section
2021-10-19 10:46:43 +03:00
allegroai
175e99b12b
Fix if queue tag default does not exist and --queue not specified, try queue name "default"
2021-10-16 23:21:45 +03:00
allegroai
2a941e3abf
Fix --stop checking default queue tag (issue #80 )
2021-10-16 23:21:12 +03:00
allegroai
3c8e0ae5db
Improve PyJWT resiliency support
2021-10-10 09:08:36 +03:00
allegroai
e416ab526b
Fix Python 3.5 compatibility
2021-09-26 00:05:08 +03:00
pollfly
e17246d8ea
Fix docstring typos ( #79 )
...
* edit doctring typo
* fix typos
2021-09-14 18:42:18 +03:00
allegroai
f6f043d1ca
Version bump to v1.1.0
2021-09-13 15:25:25 +03:00
allegroai
db57441c5d
Fix sensitive environment variable values are not masked in "executing docker" printout (issue #67 )
2021-09-13 14:00:11 +03:00
allegroai
31d90be0a1
Fix package manager config documentation (issue #78 )
2021-09-10 13:11:39 +03:00
allegroai
5a080798cb
Add support for overriding initial server connection behavior using the CLEARML_AGENT_INITIAL_CONNECT_RETRY_OVERRIDE env var (defaults to true, allows boolean value or an explicit number specifying the number of connect retries)
2021-08-27 19:15:14 +03:00
pollfly
21c4857795
Fix doctring typo ( #75 )
2021-08-22 08:19:55 +03:00
allegroai
4149afa896
Add agent.docker_internal_mounts to control containers internal mounts (non-root containers)
2021-08-21 16:03:37 +03:00
allegroai
b196ab5793
Do not overwrite PYTHONIOENCODING if defined
2021-08-20 00:37:21 +03:00
allegroai
b39b54bbaf
Add poetry cache into docker mapping (issue #74 )
2021-08-13 11:02:21 +03:00
allegroai
26d76f52ac
Fix venv cache cannot reinstall package from git with http credentials
2021-08-13 11:00:54 +03:00
allegroai
2fff28845d
Fix support for unicode standalone scripts, changing default 'ascii' encoding to UTF-8.
2021-08-12 13:39:11 +03:00
allegroai
5e4c495d62
Add support for naming docker containers. Use agent.docker_container_name_format to configure the name format (disabled by default) (issue clearml/#412)
...
Add missing entries in docs/clearml.conf
2021-08-12 13:38:26 +03:00
allegroai
5c5802c089
Fix python package with git+git:// links or git+ssh:// conversion
2021-08-12 13:37:10 +03:00
allegroai
06010ef1b7
Disable default demo server (still available with CLEARML_NO_DEFAULT_SERVER=0)
2021-08-12 13:36:49 +03:00
allegroai
bd411a1984
version bump
2021-08-05 19:23:23 +03:00
allegroai
0fbbe774fa
Fix support for "-r requirements.txt" in installed packages
2021-08-05 19:19:54 +03:00
allegroai
6b602889a5
Fix import loop
2021-08-03 01:28:08 +03:00
allegroai
cd046927f3
Add k8s glue update task status_message in hanging pods daemon
...
Fix k8s glue not throwing error when failing to push to queue
2021-08-02 22:59:31 +03:00
allegroai
5ed47d2d2c
Add support for CLEARML_NO_DEFAULT_SERVER env var to prevent agent from using the demo server
...
Add support for FORCE_CLEARML_AGENT_REPO env var to allow installing agent from a repo url when executing a task
Implement skip venv installation on execute and allow custom binary
Fix services mode limit implementation in docker mode
2021-08-02 22:51:26 +03:00
allegroai
fd068c0933
Add support for env vars containing bash-style string lists using shlex
...
Add support for CLEARML_AGENT_SKIP_PIP_VENV_INSTALL env var to skip venv installation on execute and allow custom binary
Add support for CLEARML_AGENT_VENV_CACHE_PATH env var to allow overriding venv cache folder configuration
Add support for CLEARML_AGENT_EXTRA_DOCKER_ARGS env var to allow overriding extra docker args configuration
2021-08-02 22:38:36 +03:00
Simon Gasse
9456e493ac
Enable rewriting SSH URLs
...
ClearML Agent allows to force git cloning via SSH and also has a
setting to force a username. The relevant settings are:
agent.force_git_ssh_protocol: true
agent.force_git_ssh_user: "git"
However, forcing a specific username or port only worked so far if the
agent translated either from https->ssh or from ssh->https. A given
ssh URL was not rewritten.
This commit adds a helper function and includes it in `_set_ssh_url`
to allow rewriting ssh URLs with the username and/or port given in the
config `agent.force_git_ssh_user`.
If neither username nor port are forced in the config, the URL is not
touched.
This is somewhat related to issue #42 .
Note that rewriting https->https is not covered in this commit.
2021-07-31 23:34:27 +03:00
allegroai
42606d9247
Fix multiple k8s glue instances with pod limits
...
Version bump
2021-07-15 10:28:43 +03:00
allegroai
499b3dfa66
Fix k8s glue, do not reset Task before re-enqueuing as it will remove runtime properties
2021-07-15 10:27:54 +03:00
allegroai
ca360b7d43
Improve max pod limit check
2021-07-15 10:26:49 +03:00
allegroai
6470b16b70
Add k8s set task container if using default image/arguments
2021-07-15 10:26:09 +03:00
allegroai
4c9410c5fe
Fix auto mount SSH_AUTH_SOCK into docker (issue #45 )
2021-07-11 09:44:49 +03:00
allegroai
382604e923
Fix services mode killing child processes when running in services mode + venv
2021-06-30 23:58:25 +03:00
allegroai
0e7546f248
Fix docker force pull in k8s glue _kubectl_apply()
2021-06-27 09:42:14 +03:00
allegroai
e3c8bd5666
Add support for agent.docker_force_pull configuration setting in k8s glue
2021-06-25 17:36:08 +03:00
allegroai
3ae1741343
Fix k8s glue task container arguments not supported in kubectl_run command
...
Fix k8s glue not passing required extra_docker_bash_script to string format
2021-06-25 17:35:01 +03:00
allegroai
53c106c3af
Fix k8s glue task container handling fails parsing docker image
...
Fix k8s glue uses task container image arguments when no image is specified
2021-06-25 17:34:28 +03:00
allegroai
44fc7dffe6
Fix key/secret usage printout
2021-06-24 19:37:59 +03:00
allegroai
aaa6b32f9f
Fix support for "-r requirements.txt" inside "installed packages"
2021-06-24 19:26:35 +03:00
allegroai
821a0c4a2b
Fix parsing VCS links starting with "git+git@" (notice "git+git://" was already supported)
2021-06-24 19:25:41 +03:00
allegroai
176b4a4cde
Fix --services-mode when the execute agent fails when starting to run with error code 0
2021-06-16 18:32:29 +03:00
allegroai
29bf993be7
Add printout when using key/secret from env vars
2021-06-02 21:15:48 +03:00
allegroai
eda597dea5
Version bump
2021-06-02 13:17:57 +03:00
allegroai
8c56777125
Add CLEARML_AGENT_DISABLE_SSH_MOUNT allowing disabling the auto .ssh mount into the docker
2021-06-02 13:16:58 +03:00
allegroai
7e90ebd5db
Fix _dynamic_gpu_get_available worker timeout increase to 10 minutes
2021-06-02 13:16:17 +03:00
allegroai
3a07bfe1d7
Version bump
2021-05-31 23:19:46 +03:00
allegroai
742cbf5767
Add docker environment arguments log masking support (issue #67 )
2021-05-25 19:31:45 +03:00
allegroai
e93384b99b
Fix --stop with dynamic gpus
2021-05-20 10:58:46 +03:00
allegroai
3c4e976093
Add agent.ignore_requested_python_version to config file
2021-05-19 15:20:44 +03:00
allegroai
1e795beec8
Fix support for spaces in docker arguments (issue #358 )
2021-05-19 15:20:03 +03:00
allegroai
4f7407084d
Fix standalone script with pre-exiting conda venv
2021-05-12 15:46:25 +03:00
allegroai
ae3d034531
Protect against None in execution.repository
2021-05-12 15:45:31 +03:00
allegroai
a2db1f5ab5
Remove queue name from pod name in k8s glue, add queue name and ID to pod labels (issue #64 )
2021-05-05 12:03:35 +03:00
allegroai
cec6420c8f
Version bump to v1.0.0
2021-05-03 18:33:53 +03:00
allegroai
4f18bb7ea0
Add k8s glue default restartPolicy=Never to template to prevent pods from restarting
2021-04-28 13:20:13 +03:00
Revital
24dc59e31f
add space to help message
2021-04-27 13:50:44 +03:00
allegroai
08ff5e6db7
Add number of pods limit to k8s glue
2021-04-25 10:47:49 +03:00
allegroai
e60a6f9d14
Fix --stop support for dynamic gpus
2021-04-25 10:46:43 +03:00
Revital
35e714d8d9
fix --downtime help
2021-04-21 09:13:47 +03:00
allegroai
6f8d5710d6
Fix dynamic gpus priority queue
2021-04-20 18:11:59 +03:00
allegroai
a671692832
Fix --services-mode with instance limit
2021-04-20 18:11:36 +03:00
allegroai
5c8675e43a
Add support for dynamic gpus opportunistic scheduling (with min/max gpus per queue)
2021-04-20 18:11:16 +03:00
allegroai
60a58f6fad
Fix poetry support (issue #57 )
2021-04-14 11:22:07 +03:00
allegroai
537b67e0cd
Fix agent can return non-zero error code and pods will end up restarting forever (issue #56 )
2021-04-12 23:00:59 +03:00
allegroai
82c5e55fe4
Fix usage of not_set in k8s template merge
2021-04-07 21:30:13 +03:00
allegroai
945dd816ad
Fix no docker arguments
2021-04-07 18:47:13 +03:00
allegroai
45009e6cc2
Add support for updating back docker on new API v2.13
2021-04-07 18:46:58 +03:00
allegroai
3774fa6abd
Add support for new container base setup script feature
2021-04-07 18:46:14 +03:00
allegroai
e71e6865d2
Add agent.docker_install_opencv_libs (default: True) to enable auto opencv libs install for faster docker spin-up
2021-04-07 18:45:44 +03:00
allegroai
0e8f1528b1
Remove redundant py2 code
2021-04-07 18:44:59 +03:00
allegroai
c331babf51
Add stopping message on Task process termination
...
Fix --stop on dynamic gpus venv mode
2021-04-07 18:44:33 +03:00
allegroai
c59d268995
Fix venv cache crash on bad symbolic links
2021-04-07 18:44:11 +03:00
allegroai
9e9fcb0ba9
Add dynamic mode terminate dockers on sig_term
2021-04-07 18:43:44 +03:00
allegroai
f33e0b2f78
Verify docker command exists when running in docker mode
2021-04-07 18:42:27 +03:00
allegroai
0e4b99351f
Add --stop support for dynamic gpus
...
Fix --stop mark tasks as aborted (not failed as before)
2021-04-07 18:42:10 +03:00
allegroai
81edd2860f
Fix --dynamic-gpus should keep original queue priority order
2021-03-31 23:55:12 +03:00
allegroai
14ac584577
Support k8s glue container env vars merging
2021-03-31 23:53:58 +03:00
allegroai
9ce6baf074
Fix broken k8s glue docker args parsing
...
Fix empty env prevents override when merging template
2021-03-26 12:26:15 +03:00
allegroai
92a1e07b33
Fix local path replace back when using cache
2021-03-26 12:16:05 +03:00
allegroai
cb6bdece39
Fix cuda version from driver does not return minor version
2021-03-18 10:07:59 +02:00
allegroai
2ea38364bb
Change the default conda channel order, so it pulls the correct pytorch
2021-03-18 10:07:58 +02:00
allegroai
cf6fdc0d81
Add support for PyJWT v2
2021-03-18 10:07:58 +02:00
allegroai
91eec99563
Add conda debug prints (--debug)
2021-03-18 10:07:58 +02:00
allegroai
d9b9b4984b
Version bump to v0.17.2
2021-03-04 20:12:50 +02:00
allegroai
205f9dd816
Fix k8s glue does not pass docker environment variables
...
Remove deprecated flags
2021-03-03 15:07:06 +02:00
allegroai
9dfa1294e2
Add agent.enable_task_env set the OS environment based on the Environment section of the Task.
2021-02-28 19:47:44 +02:00
allegroai
f019905720
Fix venv cache support for local folders
2021-02-28 19:47:09 +02:00
allegroai
9c257858dd
Fix venv cache support for local folders
2021-02-23 18:54:38 +02:00
allegroai
2006ab20dd
Fix conda support for git+http links
2021-02-23 12:46:06 +02:00
allegroai
0caf31719c
Fix venv caching always reinstall git repositories and local repositories
2021-02-23 12:45:34 +02:00
allegroai
5da7184276
Add agent.ignore_requested_python_version (control for multi python environments)
2021-02-23 12:45:00 +02:00
allegroai
50fccdab96
PEP8
2021-02-23 12:44:26 +02:00
allegroai
77d6ff6630
Fix docker mode without venvs cache dir
2021-02-17 00:04:07 +02:00
allegroai
58cb344ee6
Upgrade pynvml add detect CUDA version from driver level
2021-02-17 00:03:16 +02:00
allegroai
22d5892b12
Use shared git cache between multiple agents on the same machine
2021-02-14 13:49:29 +02:00
allegroai
f619969efc
Add venvs_cache configuration
2021-02-14 13:48:57 +02:00
allegroai
ca242424ab
Fix service-mode support for venvs
...
Fix --services-mode with venvs
2021-02-14 13:45:17 +02:00
allegroai
407deb84e9
Fix multi instances on Windows
2021-02-14 13:44:39 +02:00
allegroai
14589aa094
Fix CPU mode
2021-02-14 13:44:00 +02:00
allegroai
1260e3d942
Update cache entries on conda package manager
2021-02-11 14:47:26 +02:00
