Enabled MoE for both BF16 and INC based FP8 on Gaudi#1309
Draft
gyou2021 wants to merge 5 commits into
Draft
Conversation
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Ganmei You <ganmei.you@intel.com> Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: gyou2021 <ganmei.you@intel.com>
gyou2021
requested review from
afierka-intel,
jikunshang,
kzawora-intel,
madamczyk-intel,
mgawarkiewicz-intel,
michalkuligowski,
mswiniarsk,
vivekgoe and
xuechendi
as code owners
xuechendi
reviewed
May 28, 2025
| if hasattr(layer.moe_op, "w13_weight"): | ||
| layer.moe_op.w13_weight = layer.w13_weight | ||
| if hasattr(layer.moe_op, "w2_weight"): | ||
| layer.moe_op.w2_weight = layer.w2_weight |
There was a problem hiding this comment.
This is only for static moe, right?
|
Please push to vllm-fork branch, otherwise we can't trigger UT. |
|
Don't you need to update qwen RMSnorm to HPU RMSNorm? |
gyou2021
changed the title
Signed-off-by: gyou2021 <ganmei.you@intel.com>
xuechendi
force-pushed
the
dev/qwen3-habanamain
branch
from
d3012e3 to
f143727
Compare
michalkuligowski
left a comment
michalkuligowski
left a comment
There was a problem hiding this comment.
no update for 1 month converting to draft
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Enabled optimized MoE (combination of dynamic MoE and static MoE) for both BF16 and INC-based FP8.