-
Notifications
You must be signed in to change notification settings - Fork 24
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
Bump TGI version to v3.0.0 #135
Merged
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
The Dockerfile has a default value, it is easier to only maintain that.
Update to TGI 3.0.0, using a simplified Cargo.toml. This is based on the work done on optimum-neuron: huggingface/optimum-neuron#748
Starting from TGI 2.4.1, the evaluation of the default value for max_batch_prefill_tokens in the TGI launcher has changed, leading it to be set to a default value of 4096 on tpu, while it was previously set to max_batch_size * max_input_tokens. This is now fixed in the entrypoint, pending a fix in the launcher.
baptistecolle
approved these changes
Jan 6, 2025
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.
LGTM expect for small nit
Comment on lines
16
to
19
if [[ -z "${MAX_INPUT_TOKENS}" && -n ${MAX_INPUT_LENGTH} ]]; then | ||
MAX_INPUT_TOKENS=${MAX_INPUT_LENGTH} | ||
unset MAX_INPUT_LENGTH | ||
fi |
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.
Suggested change
if [[ -z "${MAX_INPUT_TOKENS}" && -n ${MAX_INPUT_LENGTH} ]]; then | |
MAX_INPUT_TOKENS=${MAX_INPUT_LENGTH} | |
unset MAX_INPUT_LENGTH | |
fi | |
if [[ -z "${MAX_INPUT_TOKENS}" && -n ${MAX_INPUT_LENGTH} ]]; then | |
MAX_INPUT_TOKENS=${MAX_INPUT_LENGTH} | |
fi | |
unset MAX_INPUT_LENGTH |
Maybe we should unset MAX_INPUT_LENGTH anyway to prevent any downstream use of it as it is deprecated
baptistecolle
approved these changes
Jan 6, 2025
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?
This bumps the TGI router version to v3.0.0. This was done by applying the changes that fixed some issues that were investigated in huggingface/optimum-neuron#748.