xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-26 08:52:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge 8625dee2c04eda7b1b091fbf1e2c511d0e4915ec into 254f6b986720c92ddf97fbb1a6a6465da8e87e29

Browse Source
This commit is contained in:
ゆり 2025-12-25 00:06:36 +00:00 committed by GitHub
commit 258b47e63c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py
View File

@ -379,13 +379,15 @@ class CompressedTensors24(CompressedTensorsScheme):
]
decompressed = combine_shards(decompressed_shards)
else:
# Use the shape loaded from the model checkpoint rather than
# computing from layer attributes, as some layer types (e.g.,
# RowParallelLinear in vision models) may not have logical_widths
# or input_size_per_partition properly initialized.
out_dim, in_dim = layer.shape.data.view(-1).tolist()
decompressed = sparsity_compressor.decompress_weight(
dict(
compressed=compressed,
shape=(
layer.logical_widths[0],
layer.input_size_per_partition,
),
shape=(out_dim, in_dim),
bitmask=bitmask,
)
)