[Model] Jamba support (#4115)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Erez Schwartz <erezs@ai21.com>
Co-authored-by: Mor Zusman <morz@ai21.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Tomer Asida <tomera@ai21.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
This commit is contained in:
Mor Zusman
2024-07-02 23:11:29 +00:00
committed by GitHub
co-authored by Erez Schwartz Mor Zusman tomeras91 Tomer Asida Zhuohan Li Muralidhar Andoorveedu
parent ee93f4f92a
commit 9d6a8daa87
21 changed files with 1192 additions and 34 deletions
+4 -3
View File
@@ -314,9 +314,10 @@ class CPUModelRunner(ModelRunnerBase[CPUModelInput]):
)
def prepare_model_input(
self,
seq_group_metadata_list: List[SequenceGroupMetadata],
virtual_engine: int = 0,
self,
seq_group_metadata_list: List[SequenceGroupMetadata],
virtual_engine: int = 0,
finished_requests_ids: Optional[List[str]] = None
) -> CPUModelInput:
multi_modal_kwargs = None
# NOTE: We assume that all sequences in the group are all prompts or