[Quant] Support compressed-tensors WNA8O8Int linears and WNInt embeddings (#44340)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-06-04 07:40:33 -07:00
committed by GitHub
parent b5235fca2e
commit 06ee2d8433
14 changed files with 744 additions and 27 deletions
+1 -1
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,<81.0.0; 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 == 0.15.0.1 # required for compressed-tensors
compressed-tensors == 0.17.0 # required for compressed-tensors
depyf==0.20.0 # 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
+1 -1
View File
@@ -28,4 +28,4 @@ quack-kernels>=0.3.3
tokenspeed-mla==0.1.2
# Humming kernels for quantization gemm
humming-kernels[cu13]==0.1.2
humming-kernels[cu13]==0.1.4
+1 -1
View File
@@ -143,7 +143,7 @@ colorful==0.5.8
# via ray
colorlog==6.10.1
# via optuna
compressed-tensors==0.15.0.1
compressed-tensors==0.17.0
# via
# -c requirements/common.txt
# -r requirements/test/../common.txt