[Quantization] Add ModelOpt IQ2_XS, IQ2_XXS, and Q8_0 support via b12x (#59604)

Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Luke Alonso <lalonso@gmail.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Luke Alonso <lalonso@gmail.com>
This commit is contained in:
Andrii Skliar
2026-10-13 09:06:33 -07:00
committed by GitHub
co-authored by Andrii Skliar Luke Alonso
parent ac71b17517
commit 6849ca696a
15 changed files with 1238 additions and 25 deletions
+3
View File
@@ -11,6 +11,9 @@ from typing import Any
import torch
# Logical elements and encoded bytes per block.
B12X_BLOCK_CODECS = {"iq2_xs": (256, 74), "iq2_xxs": (256, 66), "q8_0": (32, 34)}
@dataclass(frozen=True)
class B12xWarmupUnit: