Text generation inference, fix offline #1341
Merged
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
oOraph
force-pushed
the
dev/fix_offline
branch
4 times, most recently
from
ae77ab1
to
4959025
Compare
oOraph
commented
Dec 13, 2023
| @@ -138,33 +179,33 @@ def download_weights( | |||
| ) -> List[Path]: | |||
| """Download the safetensors files from the hub""" | |||
|
|
|||
| def download_file(filename, tries=5, backoff: int = 5): | |||
| local_file = try_to_load_from_cache(model_id, revision, filename) | |||
| def download_file(fname, tries=5, backoff: int = 5): | |||
There was a problem hiding this comment.
Note: these var renaming (filename -> fname, start_time -> stime and i -> idx) are not mandatory, just renamed them to avoid pep warnings like "shadows var_name from outer scope"
|
@OlivierDehaene @Narsil, I think the unit tests that fail only do because I miss some secrets in my forked repository. Could you please push a new branch with the proposed change in this repo (or give me the right to do it) so as to confirm this ? Thanks :) |
Signed-off-by: Raphael Glon <oOraph@users.noreply.github.com>
oOraph
force-pushed
the
dev/fix_offline
branch
from
4959025
to
b0b76ce
Compare
OlivierDehaene
added a commit
that referenced
this pull request
Dec 18, 2023
kdamaszk
pushed a commit
to kdamaszk/tgi-gaudi
that referenced
this pull request
Apr 29, 2024
@oOraph --------- Signed-off-by: Raphael Glon <oOraph@users.noreply.github.com> Co-authored-by: Raphael Glon <oOraph@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
What does this PR do?
Allows for Text Generation Inference to succeed in loading prefetched and cached private models if no token is provided at the time the text-generation-inference service is launched