🍃 Added Mixtral on TGI / Jetstream Pytorch #103
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
Note that for now serving Mixtral-8X7B is very hard due to the large amount of resources available.
Tests are split to avoid a memory problem appearing when serving different models in subsequent tests when using Jetstream/Pytorch. Here we better clarify the steps of this workflow and add Mixtral test to nightly workflow.
tengomucho
force-pushed
the
mixtral-jetstream-pt
branch
from
7b136cc
to
3b0d2e0
Compare
dacorvo
approved these changes
Oct 10, 2024
| from jetstream_pt.third_party.mixtral import config as mixtral_config | ||
| from jetstream_pt.third_party.mixtral.model import Transformer | ||
|
|
||
| #.model_exportable import Transformer, model_args |
There was a problem hiding this comment.
Looks like a leftover from an old version that was imported from gemma model that has the same comment.
tengomucho
force-pushed
the
mixtral-jetstream-pt
branch
from
38721fd
to
fa4b706
Compare
dacorvo
approved these changes
Oct 11, 2024
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Outdated suggestions cannot be applied.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?
Added support for loading and serving Mixtral models as they are supported in Jetstream Pytorch. Note, however, that serving support is limited for now, because the required memory is too big to use it in effective scenarios (for that, quantization, not supported yet, would be necessary).
A test has been added anyway.
Before submitting