quantize: Add snapshot testing #94
Open
Conversation
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
@ecyht2 I'm not sure if that's worth it. The git clone takes a long time and end users just download from Hugging Face. |
|
Hmm, maybe we can hold off on this and let @mmwillet decide. |
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Outdated suggestions cannot be applied.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.
As requested by #93 (comment) . This tests both the aliased (e.g. "Q4") and unaliased (e.g. "Q4_0") versions.
It is single-threaded as it should be IO-bound for most users. Outputing to ramdisk (default) and inputting from SSD, it takes more than 2 minutes.
The differences from my version in a comment are: CMake integration, sha256sum replacing md5sum to read from the Git cache, automating the venv/mount/git-clone initial setup, and optimization via caching or skipping gguf-dump.
This contains #93, which should be merged first.