[Misc] Clean up uesless code for LLM initialize #1373
Merged
+67
−121
Conversation
This file contains hidden or 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
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #1373 +/- ##
==========================================
- Coverage 27.39% 27.25% -0.15%
==========================================
Files 56 56
Lines 6191 6220 +29
==========================================
- Hits 1696 1695 -1
- Misses 4495 4525 +30
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
wangxiyuan
force-pushed
the
clean_up_init
branch
3 times, most recently
from
6bd5c62 to
e446e63
Compare
Yikun
reviewed
Jun 24, 2025
Comment on lines
1790
to
1793
| if self.drafter: | ||
| logger.info("Loading drafter model...") | ||
| if self.use_aux_hidden_state_outputs: | ||
| self.drafter.load_model(self.model) | ||
| else: | ||
| self.drafter.load_model() | ||
| if self.use_aux_hidden_state_outputs: | ||
| self.model.set_aux_hidden_state_layers( | ||
| self.model.get_eagle3_aux_hidden_state_layers()) | ||
| if self.use_aux_hidden_state_outputs: | ||
| self.model.set_aux_hidden_state_layers( | ||
| self.model.get_eagle3_aux_hidden_state_layers()) |
There was a problem hiding this comment.
if self.drafter:
logger.info("Loading drafter model...")
if self.use_aux_hidden_state_outputs:
self.drafter.load_model(self.model)
self.model.set_aux_hidden_state_layers(
self.model.get_eagle3_aux_hidden_state_layers())
else:
self.drafter.load_model()
also cc @yuancaoyaoHW
| @@ -1851,7 +1808,7 @@ def load_model(self) -> None: | |||
| def _get_torchair_lazy_compiled_model(self, batch_size: int): | |||
| if batch_size < 0 or batch_size > self.max_num_reqs: | |||
| raise ValueError( | |||
| f"Bad graph batch size:{batch_size}! max_num_reqs:{self.max_num_reqs}" | |||
| f"Bad graph batch size:{batch_size}! max_num_seqs:{self.max_num_reqs}" | |||
There was a problem hiding this comment.
Suggested change
| f"Bad graph batch size:{batch_size}! max_num_seqs:{self.max_num_reqs}" | |
| f"Bad graph batch size:{batch_size}! max_num_reqs:{self.max_num_reqs}" |
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
wangxiyuan
force-pushed
the
clean_up_init
branch
from
e446e63 to
4e0967a
Compare
zkryakgul
added a commit
to zkryakgul/vllm-ascend
that referenced
this pull request
Jun 25, 2025
[Misc] Clean up uesless code for LLM initialize (vllm-project#1373)
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.
This PR aims to clean up the useless code for LLM setup. It helps to make the code more clear.
self.xxxpropertyset_random_seedtoseed_everythingset_custom_all_reduce, it's only used for cudaThis is just a code clean. no change for any code logic.