Add dynamic KVCache and metadata resolution to support Qwen3 serving.#208
Open
copybara-service[bot] wants to merge 1 commit into
Open
Add dynamic KVCache and metadata resolution to support Qwen3 serving.#208copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
This change enables Raiden-LM serving support for the Qwen3 model family: - Scans entry parameter list dynamically to resolve request_distribution index. - Dynamically derives KVCacheManager layer count and block slice_byte_size from HLO argument shapes. - Connects the max_tokens benchmark flag to SessionConfig. PiperOrigin-RevId: 938946803
copybara-service
Bot
force-pushed
the
test_938946803
branch
from
7872a41 to
be2e8e9
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add dynamic KVCache and metadata resolution to support Qwen3 serving.
This change enables Raiden-LM serving support for the Qwen3 model family: