[WIP][V0.9.1] add support for flashcomm2 in qwen2 #1850
+258
−21
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: David9857 <[email protected]>
Signed-off-by: David9857 <[email protected]>
David9857
changed the title
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Signed-off-by: David9857 <[email protected]>
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Outdated suggestions cannot be applied.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 this PR does / why we need it?
Same changes as #1726 but for qwen2.
Note: Enabling FlashComm in decoding stage may cause increased latency, so it is recommended to use disaggregated prefilling and enbale this feature in the prefill instance only!!!
Does this PR introduce any user-facing change?
How was this patch tested?