[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:
co-authored by
Andrii Skliar
Luke Alonso
parent
ac71b17517
commit
6849ca696a
@@ -584,6 +584,8 @@ class NemotronHModel(nn.Module, EagleModelMixin):
|
||||
self.embed_tokens = VocabParallelEmbedding(
|
||||
self.vocab_size,
|
||||
config.hidden_size,
|
||||
quant_config=quant_config,
|
||||
prefix=f"{prefix}.embed_tokens",
|
||||
)
|
||||
|
||||
self.has_moe = "E" in config.hybrid_override_pattern
|
||||
|
||||
Reference in New Issue
Block a user