-
Notifications
You must be signed in to change notification settings - Fork 7
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
0.4 #70
Open
JadenFiotto-Kaufman
wants to merge
66
commits into
dev
Choose a base branch
from
0.4
base: dev
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
0.4 #70
+1,110
−578
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
…d redirecting them to login.ndif.us if not)
…ts in model base.
…dif with a local editable nnsight repo
Streamed execution
Add live dependency updates and auto-update on container start
…n. It updates an unused env var in the chosen applications config and then redeploys. This causes Ray to restart the Deployment. Model deployments trigger this remote method with their application name when they hit a CUDA device side assert error as its the only way to uncorrupt its cuda runtime
Added remote method to Controller deployment to restart an applicatio…
…CCL process and torch distributed process group from being terminated on timeout. Vastly simplifies timeouts
Docker Refactoring
Observability 0.4
All of the model keys in the various service configs should be updated to the new schema ( |
…ng at a given time. Increase number of ongoing/queues requests to a reasonable number
add gpu_mem metric, remove gpu_mem from request_status metric
…ents the status endpoint from having to get the status directly from the model endpoint as they might be blocked by a job
Refactor metrics
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.