biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Refactor MOE NVFP4 Code Base: ModelOpt + Compressed Tensor (#21631)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2025-07-27 08:25:21 -04:00
committed by GitHub
parent 3d847a3125
commit bda9d0535f
6 changed files with 75 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/quantization/test_compressed_tensors.py
View File

@@ -17,7 +17,9 @@ from vllm.model_executor.layers.quantization.compressed_tensors.compressed_tenso
CompressedTensorsW4A4Fp4, CompressedTensorsW4A16Fp4,
CompressedTensorsW4A16Sparse24, CompressedTensorsW8A8Fp8,
CompressedTensorsW8A8Int8, CompressedTensorsW8A16Fp8,
CompressedTensorsWNA16, cutlass_fp4_supported)
CompressedTensorsWNA16)
from vllm.model_executor.layers.quantization.utils.quant_utils import (
cutlass_fp4_supported)
from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
sparse_cutlass_supported)
from vllm.platforms import current_platform