mirror of
https://github.com/hanzo-ml/trainer.git
synced 2026-09-24 00:31:34 +00:00
88a92a0483
* feat: support for flux framework as hpc manager Flux supports the majority of MPI flavors/variants, and can be used to bootstrap MPI as a plugin. It adds other features for scheduling and topology that can be used for simulations and ai/ml jobs. This changeset adds the plugin implementation, including the plugin module, tests, and an example with a small README to serve as documentation for the time being. Signed-off-by: vsoch <[email protected]> * review: slim down use of annotations We still need to put the original command in an annotation to retieve later, but others can be re-derived from the environment Signed-off-by: vsoch <[email protected]> * review: clean up tasks and remove extra FluxPolicySource Signed-off-by: vsoch <[email protected]> * review: ensure to unset trainer args Signed-off-by: vsoch <[email protected]> * review: better support for nproc per node and nodes Signed-off-by: vsoch <[email protected]> * review: add constants types for flux Signed-off-by: vsoch <[email protected]> * review: add gpu specification from resources Signed-off-by: vsoch <[email protected]> * Fix TrainJob NumProcPerNode Signed-off-by: Andrey Velichkevich <[email protected]> * Remove elasticPolicy from kubebuilder:validation Signed-off-by: Andrey Velichkevich <[email protected]> * chore: use go embed for long string templates flux plugin Signed-off-by: vsoch <[email protected]> * cleanup: removed un-used annotation Signed-off-by: vsoch <[email protected]> --------- Signed-off-by: vsoch <[email protected]> Signed-off-by: Andrey Velichkevich <[email protected]> Co-authored-by: vsoch <[email protected]> Co-authored-by: Andrey Velichkevich <[email protected]>
25 lines
476 B
TOML
25 lines
476 B
TOML
[access]
|
|
allow-guest-user = true
|
|
allow-root-owner = true
|
|
|
|
# Point to resource definition generated with flux-R(1).
|
|
[resource]
|
|
path = "/mnt/flux/config/etc/flux/system/R"
|
|
|
|
[bootstrap]
|
|
curve_cert = "/mnt/flux/config/etc/curve/curve.cert"
|
|
default_port = 8050
|
|
default_bind = "%s"
|
|
default_connect = "%s"
|
|
hosts = [
|
|
{ host="%s"},
|
|
]
|
|
|
|
[archive]
|
|
dbpath = "/mnt/flux/config/var/lib/flux/job-archive.sqlite"
|
|
period = "1m"
|
|
busytimeout = "50s"
|
|
|
|
[sched-fluxion-qmanager]
|
|
queue-policy = "%s"
|