xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 04:44:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] upgrade compressed-tensors to 0.12.2 to address LGPLv3 (#26501)

Browse Source 
Signed-off-by: Sangyeon Cho <josang1204@gmail.com>
This commit is contained in:
Sangyeon Cho 2025-10-14 01:58:33 +09:00 committed by GitHub
parent 5c7fe25491
commit a1b2d658ee
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements/common.txt
View File

@ -38,7 +38,7 @@ pyyaml
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
setuptools>=77.0.3,<80; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
einops # Required for Qwen2-VL.
compressed-tensors == 0.11.0 # required for compressed-tensors
compressed-tensors == 0.12.2 # required for compressed-tensors
depyf==0.19.0 # required for profiling and debugging with compilation config
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
watchfiles # required for http server to monitor the updates of TLS files

2
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
View File

@ -310,7 +310,7 @@ class CompressedTensorsConfig(QuantizationConfig):
)
is_float_type = (
weight_quant.type == QuantizationType.FLOAT
and input_quant.type == QuantizationType.FLOAT.value
and input_quant.type == QuantizationType.FLOAT
)
is_4_bits = weight_quant.num_bits == 4 and input_quant.num_bits == 4

2
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
View File

@ -143,7 +143,7 @@ class CompressedTensorsMoEMethod(FusedMoEMethodBase):
# Prefer to use the MarlinMoE kernel when it is supported.
if not check_moe_marlin_supports_layer(layer, group_size):
if (
weight_quant.strategy in QuantizationStrategy.GROUP
weight_quant.strategy == QuantizationStrategy.GROUP
and weight_quant.actorder
in (ActivationOrdering.GROUP, ActivationOrdering.DYNAMIC)
):