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Outdated suggestions cannot be applied.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.
As
microsoft/Phi-3-mini-4k-instruct
is using fusedqkv_proj
andup_gate_proj
, LoRA adapters should be applied to each chunk instead of the entire fused matrix.The change lies in (1) adapter initialization and (2) forward computing.
For (1), we create
n_chunk
adapters for one fused matrix,default-chunk-0
,default-chunk-1
, ... for both lora_A and lora_B.For (2), we iterate the adapter by
adapter_name
. Once we find its chunk, we only update the associated dense result.We have run the
make style
andmake quality
.