Skip to content

[Deploy] Finalize Gateway/Proxy port during device binding.#2167

Merged
Raphael-Jin merged 6 commits intodev/v0.7.0from
raphael/hotfix-inference-port
Jun 13, 2024
Merged

[Deploy] Finalize Gateway/Proxy port during device binding.#2167
Raphael-Jin merged 6 commits intodev/v0.7.0from
raphael/hotfix-inference-port

Conversation

@Raphael-Jin
Copy link
Copy Markdown
Collaborator

No description provided.

@Raphael-Jin Raphael-Jin changed the title [Deploy] Initial Gateway/Proxy based on the env variables. [Deploy] Initialize Gateway/Proxy based on the env variables. Jun 12, 2024
Comment thread python/fedml/computing/scheduler/model_scheduler/master_job_runner.py Outdated
inference_port = model_config_parameters.get("server_internal_port",
ServerConstants.MODEL_INFERENCE_DEFAULT_PORT)
inference_port_external = model_config_parameters.get("server_external_port", inference_port)
inference_port_external = os.environ.get(ServerConstants.ENV_MASTER_INFERENCE_PORT_KEY,
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about centralizing the reads by adding static methods, one in Server Constant for master port and another in Client Constants for worker port?

@Raphael-Jin Raphael-Jin changed the title [Deploy] Initialize Gateway/Proxy based on the env variables. [Deploy] Finalize Gateway/Proxy port during device binding. Jun 12, 2024
@alaydshah
Copy link
Copy Markdown
Contributor

Looks good to me 👍🏻

@Raphael-Jin Raphael-Jin merged commit bec28a6 into dev/v0.7.0 Jun 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants