biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Jamba support (#4115)

Browse Source 
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
2024-07-03 02:11:29 +03:00
committed by GitHub
parent ee93f4f92a
commit 9d6a8daa87
21 changed files with 1192 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/sequence.py
View File

@@ -934,6 +934,8 @@ class ExecuteModelRequest:
previous_hidden_states: Optional[HiddenStates] = None
# The number of forward steps to run.
num_steps: int = 1
# Finished request ids since last step.
finished_requests_ids: List[str] = field(default_factory=list)
def clone(
self, seq_group_metadata_list: List[SequenceGroupMetadata]
@@ -949,4 +951,4 @@ class ExecuteModelRequest:
running_queue_size=self.running_queue_size,
previous_hidden_states=self.previous_hidden_states,
num_steps=self.num_steps,
)
finished_requests_ids=self.finished_requests_ids)