Fill gaps from assistant conversations: GPU sizing and HF downloads#300
Open
mintlify[bot] wants to merge 3 commits into
Open
Fill gaps from assistant conversations: GPU sizing and HF downloads#300mintlify[bot] wants to merge 3 commits into
mintlify[bot] wants to merge 3 commits into
Conversation
Contributor
Author
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
Contributor
Author
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Address recurring assistant questions about how to pick a GPU for a given model size and how to avoid downloading entire Hugging Face repositories to persistent storage.
Changes
hardware/using-gpus.mdx: added a "Choosing a GPU for your model" section with a VRAM sizing rule of thumb, a mapping from loaded weight size to typical single-GPU options, and a note on quantized formats and multi-GPU sharding.performance/faster-cold-starts.mdx: called out thatHF_HOMEis set to persistent storage automatically and added a "Download only the files you need" subsection withsnapshot_downloadexamples usingallow_patterns/ignore_patterns.Context
Recent assistant threads showed users repeatedly asking which GPU fits an N-GB model, whether Cerebrium downloads the full HF repo, and how to trim model files before deploying — all answerable from the docs but not covered directly on the relevant pages.