added 2,3,8 bit support for eora kernel #1392
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
hutm
requested review from
Qubitium and
ZX-ModelCloud
and removed request for
ZX-ModelCloud
Signed-off-by: Qubitium <[email protected]>
Signed-off-by: Qubitium <[email protected]>
Qubitium
approved these changes
Mar 7, 2025
Qubitium
added a commit
that referenced
this pull request
Mar 12, 2025
* eora release wip * fix calibration dataset bug and eora inference batch size larger than 1 bug * added 2,3,8 bit support for eora kernel (#1392) * added 2,3,8 bit support for eora kernel * added 2 and 3 bits to eora sweep test, fixed contiguous() * check compatible bit range before fused op Signed-off-by: Qubitium <[email protected]> * format Signed-off-by: Qubitium <[email protected]> --------- Signed-off-by: Qubitium <[email protected]> Co-authored-by: Qubitium <[email protected]> * . * finish eora documentation * finish eora documentation * finish eora documentation --------- Signed-off-by: Qubitium <[email protected]> Co-authored-by: Maksim Khadkevich <[email protected]> Co-authored-by: Qubitium <[email protected]>
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Outdated suggestions cannot be applied.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.
added support for 2,3,8 bit kernels
8bit kernel has issues: need to confirm GPTQ quantized tensors shapes
2, 3 bits work flawlessly