-
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
Adding reference guide for storage optimization for inference with GCSFuse #126
Conversation
Add sotrage benchmarking adding storage benchmark for GCSFuse adding sotrage benchmark Adding storage benchmarking adding storage benchmarking Adding storage benchmarking adding storage benchmarking adding storage benchmarking add storage benchmarking Adding storage benchmarking Add storage benchmarking Adding storage benchmarking Adding storage benchmarking Adding storage benchmarking Adding storage benchmarking Adding storage benchmarking Adding storage benchmarking Adding storage benchmarking guide Adding storage benchmarking guide Adding storage benchmarking guide Adding storage benchmarking guide Adding storage benchmarking guide Adding storage benchmarking guide Adding storage benchmarking guide Adding reference guide for storage optimization for inference
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.
Initial quick review, will do some additional testing and in-depth review.
use-cases/prerequisites/manifests/transfer-llama-to-flat-gcs-a100-dws.yaml
Outdated
Show resolved
Hide resolved
use-cases/prerequisites/manifests/transfer-llama-to-hierarchical-gcs-a100-dws.yaml
Outdated
Show resolved
Hide resolved
...ost-optimization/storage-benchmarking/gcsfuse/manifests/model-deployment-tuned-a100-dws.yaml
Outdated
Show resolved
Hide resolved
...cing/cost-optimization/storage-benchmarking/gcsfuse/manifests/model-deployment-a100-dws.yaml
Outdated
Show resolved
Hide resolved
...ost-optimization/storage-benchmarking/gcsfuse/manifests/provisioning-request-tuned-a100.yaml
Outdated
Show resolved
Hide resolved
use-cases/prerequisites/manifests/provisioning-request-flat-gcs-a100.yaml
Outdated
Show resolved
Hide resolved
use-cases/prerequisites/manifests/provisioning-request-hierarchical-gcs-a100.yaml
Outdated
Show resolved
Hide resolved
use-cases/prerequisites/manifests/transfer-llama-to-flat-gcs-a100-dws.yaml
Outdated
Show resolved
Hide resolved
use-cases/prerequisites/manifests/transfer-llama-to-hierarchical-gcs-a100-dws.yaml
Outdated
Show resolved
Hide resolved
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.
I didn't manage to conclude the execution because I got stuck in copying model from hf to gcs due to lack of GPU availability. So, I've added a few suggestions to this part of the tutorial to simplify user experience
use-cases/inferencing/cost-optimization/storage-benchmarking/README.md
Outdated
Show resolved
Hide resolved
use-cases/inferencing/cost-optimization/storage-benchmarking/gcsfuse/README.md
Outdated
Show resolved
Hide resolved
use-cases/inferencing/cost-optimization/storage-benchmarking/gcsfuse/README.md
Outdated
Show resolved
Hide resolved
10da4be
to
4b0b27e
Compare
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.
The READMEs can use a little bit more polishing, but I'll submit my recommendations as a follow up PR.
use-cases/inferencing/cost-optimization/gcsfuse/manifests/model-deployment-a100-dws.yaml
Show resolved
Hide resolved
use-cases/inferencing/cost-optimization/gcsfuse/manifests/model-deployment-tuned-a100-dws.yaml
Show resolved
Hide resolved
…SFuse Adding reference guide for storage optimization for inference with GCSFuse Adding reference guide for storage optimization for inference with GCSFuse Combining llama transfer to two GCS buckets in on job Combining llama transfer to two GCS buckets in on job Combining llama transfer to two GCS buckets in on job Adding reference guide for storage optimization for inference with GCSFuse Adding reference guide for storage optimization for inference with GCSFuse Adding reference guide for storage optimization for inference with GCSFuse Adding reference guide for storage optimization for inference with GCSFuse Adding reference guide for storage optimization for inference with GCSFuse
b4a915e
to
41ff9ae
Compare
* Adding reference guide for storage optimization for inference with GCSFuse (#126) --------- Co-authored-by: Shobhit Gupta <[email protected]>
No description provided.