feat: add tokenize endpoint #1650
Draft
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
Signed-off-by: yxia216 <[email protected]>
Signed-off-by: yxia216 <[email protected]>
Signed-off-by: yxia216 <[email protected]>
Signed-off-by: yxia216 <[email protected]>
dosubot
bot
added
the
size:XXL
mathetake
requested changes
Dec 15, 2025
Member
There was a problem hiding this comment.
- Can you delete the entire examples/tokenize example yamls as they are irrelevant here ie. no specific config to tokenize endpoint. If you think about it, we don't have yamls for /messages /rerank, etc.
- Let's start small for the new feature like this instead of sending a giant PR. E.g. start with only AWS bedrock. That would be helpful for you to land code faster but also helping reviewers a lot. So could you remove the other code like gcp translation etc.
Member
|
@hustxiayang I see you left TODOs in the description -- so let me mark the PR as draft until if you feel ready for review after resolving them. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
I get these fields from vLLM: https://github.com/vllm-project/vllm/blob/d2c919dcc20b1ea77a94fa01e813ebbb31f8a66a/vllm/entrypoints/openai/protocol.py#L1897
TODO: remove the fields related to transformers, these should not be generic.
Something needs to be discussed:
1 I want to name it as
OpenAIalthough tokenize endpoint is not supported in OpenAI models. The reason is that these fields are from OpenAI.TODO:
For OpenAI models, we can just use golang binding for https://github.com/openai/tiktoken.