[JAX][Quantization] Add Qwix support for SparseMatul #740
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
jrplatin
force-pushed
the
jacobplatin/ds-sparse-matmul-qwix
branch
3 times, most recently
from
dc66730 to
1ad3d95
Compare
liudangyi
reviewed
Sep 25, 2025
jrplatin
force-pushed
the
jacobplatin/ds-sparse-matmul-qwix
branch
from
1ad3d95 to
c1c5ace
Compare
jrplatin
changed the title
liudangyi
reviewed
Sep 29, 2025
tpu_commons/models/jax/utils/quantization/quantization_utils.py
Outdated
Show resolved
Hide resolved
bzgoogle
approved these changes
Sep 30, 2025
Signed-off-by: bzgoogle <beinuoz@google.com>
Signed-off-by: bzgoogle <beinuoz@google.com>
Signed-off-by: bzgoogle <beinuoz@google.com>
Signed-off-by: Jacob Platin <jacobplatin@google.com>
Signed-off-by: Jacob Platin <jacobplatin@google.com>
Signed-off-by: Jacob Platin <jacobplatin@google.com>
Signed-off-by: Jacob Platin <jacobplatin@google.com>
jrplatin
force-pushed
the
jacobplatin/ds-sparse-matmul-qwix
branch
from
1c020fd to
0eea95b
Compare
bzgoogle
pushed a commit
that referenced
this pull request
Oct 3, 2025
Signed-off-by: Jacob Platin <jacobplatin@google.com>
bzgoogle
pushed a commit
that referenced
this pull request
Oct 30, 2025
Signed-off-by: Jacob Platin <jacobplatin@google.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Outdated suggestions cannot be applied.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.
Description
In this PR, I add manual Qwix weight quantization and activation quantization for
SparseMatmulinDeepSeekMoE. This is needed becauseqwix.quantize_modeldoes not work nicely with theshard_mapthat we are using (which hides Qwix metadata).Tests
Added relevant unit testing + tested with and without
sparse_matmulandskip_quantization.Checklist
Before submitting this PR, please make sure: