Add Pytorch Tensor Parallel support for Qwen2, Qwen2Moe, Starcoder2 #35007
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
|
Hey @ArthurZucker! This PR is ready for review, please, take a look. |
VladOS95-cyber
force-pushed
the
add-tensor-parallel-support-for-qwen2
branch
2 times, most recently
from
2601f22 to
73d5df4
Compare
|
I think I should Fix Starcoder2 as well |
VladOS95-cyber
force-pushed
the
add-tensor-parallel-support-for-qwen2
branch
from
73d5df4 to
6d6014e
Compare
VladOS95-cyber
changed the title
4 tasks
|
Thanks, sorry a bit slow this week, reviewing asap! |
VladOS95-cyber
force-pushed
the
add-tensor-parallel-support-for-qwen2
branch
from
8228ce7 to
7292f79
Compare
VladOS95-cyber
force-pushed
the
add-tensor-parallel-support-for-qwen2
branch
from
7292f79 to
8da9c10
Compare
ArthurZucker
approved these changes
Dec 4, 2024
|
Thanks @VladOS95-cyber 🤗 |
BernardZach
pushed a commit
to BernardZach/transformers
that referenced
this pull request
Dec 5, 2024
…uggingface#35007) * add base tp plan for qwen2 and qwen2moe * add parallel tp for starcoder2 * fix modular conversion * add infer dim for qkv states * Update src/transformers/models/qwen2_moe/configuration_qwen2_moe.py --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
BernardZach
pushed a commit
to innovationcore/transformers
that referenced
this pull request
Dec 6, 2024
…uggingface#35007) * add base tp plan for qwen2 and qwen2moe * add parallel tp for starcoder2 * fix modular conversion * add infer dim for qkv states * Update src/transformers/models/qwen2_moe/configuration_qwen2_moe.py --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
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.
What does this PR do?
This PR uses the torch.distributed.tensor.parallel subpackage to implement Tensor Parallel for Qwen2, Qwen2Moe, Starcoder2.
Fix qkv states dims for Mistral
Before submitting
Pull Request section?
to it if that's the case. Link: Add
Tensor Parallelsupport for ALL models #34789documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@ArthurZucker