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

Refactor NVFP4 Linear utils for ModelOpt and CT (#33201)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-01-30 19:37:42 -05:00
committed by GitHub
parent 2b465570e6
commit 67ebaff528
12 changed files with 462 additions and 483 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/test_compressed_tensors.py
View File

@@ -24,7 +24,7 @@ from vllm.model_executor.layers.quantization.compressed_tensors.compressed_tenso
)
from vllm.model_executor.layers.quantization.input_quant_fp8 import QuantFP8
from vllm.model_executor.layers.quantization.utils.fp8_utils import W8A8BlockFp8LinearOp
from vllm.model_executor.layers.quantization.utils.quant_utils import (
from vllm.model_executor.layers.quantization.utils.nvfp4_utils import (
cutlass_fp4_supported,
)
from vllm.model_executor.layers.quantization.utils.w8a8_utils import (