-
Notifications
You must be signed in to change notification settings - Fork 9
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
[batch infer] Update batch inference template to use RayLLMBatch #346
Merged
Merged
Changes from all commits
Commits
Show all changes
7 commits
Select commit
Hold shift + click to select a range
c85a6b8
update ipython
bac0d25
update readme
d2c62a5
update
1927120
update
01c0475
Update templates/batch-llm/README.ipynb
rickyyx 76c7439
Update with comments and fix GCP compute config (#352)
rickyyx 9725f93
Merge branch 'main' into raysummit-batchllm
rickyyx File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,84 +1,4 @@ | ||
| head_node_type: | ||
| name: head-node | ||
| instance_type: m5.2xlarge | ||
| resources: | ||
| cpu: 0 | ||
| worker_node_types: | ||
| - name: worker-g5-xlarge-nvidia-a10-1 | ||
| instance_type: g5.xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 4 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-2xlarge-nvidia-a10-1 | ||
| instance_type: g5.2xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 4 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-4xlarge-nvidia-a10-1 | ||
| instance_type: g5.4xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 4 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-8xlarge-nvidia-a10-1 | ||
| instance_type: g5.8xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 4 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-12xlarge-nvidia-a10-4 | ||
| instance_type: g5.12xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 1 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-16xlarge-nvidia-a10-1 | ||
| instance_type: g5.16xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 4 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-24xlarge-nvidia-a10-4 | ||
| instance_type: g5.24xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 1 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| - name: worker-g5-48xlarge-nvidia-a10-8 | ||
| instance_type: g5.48xlarge | ||
| resources: | ||
| custom_resources: | ||
| "accelerator_type:A10G": 1 | ||
| min_workers: 0 | ||
| max_workers: 1 | ||
| use_spot: true | ||
| fallback_to_ondemand: true | ||
| aws: | ||
| TagSpecifications: | ||
| - ResourceType: instance | ||
| Tags: | ||
| - Key: as-feature-multi-zone | ||
| Value: "true" | ||
| name: head | ||
| # TODO(ricky): We need head node to have CUDA due to eager import from rayllm_batch now. | ||
| instance_type: g5.xlarge | ||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| head_node_type: | ||
| name: head | ||
| # TODO(ricky): We need head node to have CUDA due to eager import from rayllm_batch now. | ||
| instance_type: g2-standard-4-nvidia-l4-1 |
This file was deleted.
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we generally don't want to encourage the pattern of using GPU head nodes --> since it leads to people running code on head nodes that take down the workload due to oom (antipattern)
can you use a CPU head node instead with scheduling disabled (see basic serverless config that existing templates use) and wrap your code in an actor or something that runs on workers?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This makes sense - instead of temp fixing this by wrapping in actor, I think we will fix this by addressing the root cause soon, that is to make this code runnable on CPU itself (which it should be, it's just we are not lazy importing vllm as of now).