[Core][Model] Gemma4: Unified FA4 for all layers + FlashAttention mm_prefix support (#42175)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
co-authored by
Luciano Martins
Lucas Wilkinson
Matthew Bonanni
parent
d82ac00923
commit
6deb05e0e4
@@ -73,6 +73,11 @@ class DFlashProposer(SpecDecodeBaseProposer):
|
||||
@override
|
||||
def _create_draft_vllm_config(self) -> VllmConfig:
|
||||
base = super()._create_draft_vllm_config()
|
||||
# The draft model is text-only — clear the target's multimodal
|
||||
# flag so flash_attn is not rejected for mm_prefix support.
|
||||
arch = base.model_config.model_arch_config
|
||||
if arch.is_mm_prefix_lm:
|
||||
base.model_config.model_arch_config = replace(arch, is_mm_prefix_lm=False)
|
||||
return replace(
|
||||
base,
|
||||
attention_config=replace(
|
||||
|
||||
Reference in New Issue
Block a user