vllm/model_executor/layers/linear.py · d886c26d4d4fef7d079696beb4ece1cfb4b008a8 · OpenDAS / vllm_cscc

[Bugfix][Quantization] Fix PerTensorScale loading with tuple shard_id in... · 98e1a43a

kkyyxhll authored Apr 07, 2026


[Bugfix][Quantization] Fix PerTensorScale loading with tuple shard_id in MergedColumnParallelLinear (#38517)
Signed-off-by: loukang <loukang@xiaohongshu.com>

98e1a43a

linear.py 60.7 KB

Replace linear.py