Support pipeline parallel for glm-4-9b-chat #11463
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
plusbang
force-pushed
the
support-glm4-pp
branch
from
714ea50 to
e0f3be7
Compare
plusbang
changed the title
xiangyuT
reviewed
Jul 2, 2024
| inputs_embeds = self.embedding(input_ids) | ||
| else: | ||
| batch_size, seq_length, _ = inputs_embeds.shape |
There was a problem hiding this comment.
If attention_mask is given a not-None and not-All value, input_ids is needed in line 58 self.get_masks() and it will raise error if input_ids is still None. Maybe add an empty tensor here?
input_ids = torch.empty((batch_size, seq_length), device=inputs_embeds.device)There was a problem hiding this comment.
Relative code in modeling_chatglm:
def get_masks(self, input_ids, past_key_values, padding_mask=None):
batch_size, seq_length = input_ids.shapeThere was a problem hiding this comment.
If attention_mask is given a not-None and not-All value,
input_idsis needed in line 58self.get_masks()and it will raise error ifinput_idsis still None. Maybe add an empty tensor here?
Have updated in chatglm2.py and chatglm4.py.
RyuKosei
pushed a commit
to RyuKosei/ipex-llm
that referenced
this pull request
Jul 19, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Support pipeline parallel inference & serving for glm-4-9b-chat
2. User API changes
N/A
4. How to test?