[Bug fix] Fix cudagraph when use ep. #3130
Merged
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
|
Thanks for your contribution! |
Wanglongzhi2001
force-pushed
the
fix_ep_cudagraph
branch
from
b34de26 to
dc6d657
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Fix cudagraph when use ep.
Dataset: 200 prompts
model: ERNIE-4_5-300B-A47B-FP8-Paddle
Version of paddle: 3.0.1
max_model_len：32768
content of pr
When
max_model_lenis large such as 32k, thefull_lengthof_dummy_prefill_inputsfunction will be 4k，and the received token num of EP will be very large such as 19w, then the buffer size of DeepEP maybe not enough and then causenanproblem. So I reduce the full length when use EP.comparison result