add renormalize param for FusedMOE #671
Open
+1
−1
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
tangleintel
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz and
vivekgoe
as code owners
kwisniewski98
approved these changes
Jan 13, 2025
michalkuligowski
requested changes
Jan 14, 2025
| @@ -235,7 +235,7 @@ def __init__( | |||
| from vllm.model_executor.layers.quantization.inc import INCConfig | |||
| selected_fused_moe = (StaticFusedMOE if isinstance( | |||
| quant_config, INCConfig) else DynamicFusedMOE) | |||
| self.hpu_static_fused_moe = selected_fused_moe(self.num_experts) | |||
| self.hpu_static_fused_moe = selected_fused_moe(self.num_experts, renormalize=renormalize) | |||
There was a problem hiding this comment.
Hi, you will need to update sha for vllm-hpu-extension in requirements-hpu.txt when additional PR is merged
There was a problem hiding this comment.
OK, thx for the reminder, I will do it.
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Outdated suggestions cannot be applied.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.
Add renormalize parameter for FusedMOE cause whether to normalize routing_weights depends on the norm_topk_prob attrib in model's config.json file. Some models such as Qwen2-MoE is set to false.
Note: This PR should depend on this one in vllm-hpu-extension. So pls also help review it first.