[Bugfix][Speculative Decoding] Fix Eagle3 quantization config inheritance #120
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
…ance Eagle3 drafters were incorrectly inheriting the verifier's quantization configuration instead of using their own, causing KeyError when loading unquantized drafter weights with quantized verifiers. This implements a clean inheritance pattern where: - Base LlamaDecoderLayer has configurable get_quant_config() method - Eagle3 LlamaDecoderLayer overrides to use drafter's quantization config - Uses existing VllmConfig._get_quantization_config() infrastructure Fixes speculative decoding with quantized verifier + unquantized drafter. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]> Signed-off-by: [email protected] Signed-off-by: Rahul Tuli <[email protected]>
Member
Author
|
Landed on vllm main! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Eagle3 drafters were incorrectly inheriting the verifier's quantization
configuration instead of using their own, causing KeyError when loading
unquantized drafter weights with quantized verifiers.
This implements a clean inheritance pattern where: