[Bugfix] Pass quant_config to DiffusionGemma's ParallelLMHead (#48521)
Signed-off-by: Aaron Kang <aaron.h.kang@icloud.com> Co-authored-by: Misha Goin <mgoin64@gmail.com>
This commit is contained in:
@@ -250,6 +250,8 @@ class DiffusionGemmaForConditionalGeneration(
|
||||
self.lm_head = ParallelLMHead(
|
||||
num_embeddings=text_config.vocab_size,
|
||||
embedding_dim=text_config.hidden_size,
|
||||
quant_config=vllm_config.quant_config,
|
||||
prefix=maybe_prefix(prefix, "lm_head"),
|
||||
)
|
||||
|
||||
if text_config.tie_word_embeddings:
|
||||
|
||||
Reference in New Issue
Block a user