[Refactor] Remove dead code quantization 2 (#52821)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Wentao Ye
2026-08-25 20:28:44 -07:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 7156c63bef
commit a5e0045433
14 changed files with 0 additions and 526 deletions
@@ -67,7 +67,6 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
kFp8StaticTensorSym,
)
from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
cutlass_block_fp8_supported,
cutlass_fp8_supported,
normalize_e4m3fn_to_e4m3fnuz,
)
@@ -252,7 +251,6 @@ class Fp8LinearMethod(LinearMethodBase):
def __init__(self, quant_config: Fp8Config):
self.quant_config = quant_config
self.is_scale_e8m0 = getattr(quant_config, "is_scale_e8m0", False)
self.cutlass_block_fp8_supported = cutlass_block_fp8_supported()
self.out_dtype = torch.get_default_dtype()
self.input_dtype = get_current_vllm_config().model_config.dtype