[Spec Decoding] Use target model max length as default for draft model #7706
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
We currently assume a hard-coded default of 2k for the max model length in the case that it can't be inferred from the model's configuration. In the case of spec decoding draft models, it would instead be better to assume the same max length of the target model in this case. This is particularly helpful for MLPSpeculator models whose length can't be determined from their config.json files and should be assumed to match that of the corresponding target model that they were specifically trained for.
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
DarkLight1337
approved these changes
Aug 21, 2024
patrickvonplaten
pushed a commit
to patrickvonplaten/vllm
that referenced
this pull request
Aug 21, 2024
omrishiv
pushed a commit
to omrishiv/vllm
that referenced
this pull request
Aug 26, 2024
Alvant
pushed a commit
to compressa-ai/vllm
that referenced
this pull request
Oct 26, 2024
vllm-project#7706) Signed-off-by: Alvant <alvasian@yandex.ru>
KuntaiDu
pushed a commit
to KuntaiDu/vllm
that referenced
this pull request
Nov 20, 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Outdated suggestions cannot be applied.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.
We currently assume a hard-coded default of 2k for the max model length in the case that it can't be inferred from the model's configuration.
In the case of spec decoding draft models, it would instead be better to assume the same max length of the target model in this case.
This is particularly helpful for MLPSpeculator models whose length can't be determined from their config.json files and should be assumed to match that of the corresponding target model that they were specifically trained for.