vllm/lora/layers/row_parallel_linear.py · 0cca9b4d130b4caddb60086ef26a0d8741582dcb · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Bugfix] Fix precision loss in LoRA-wrapped RowParallelLinear by fusing bias into GEMM (#28972) · 0cca9b4d
prashanth058 authored Nov 19, 2025
```
Signed-off-by: prashanth058 <prashanth.dannamaneni@uipath.com>
```
0cca9b4d

row_parallel_linear.py 6.03 KB