refine awq, bugfix - #2115
Open
WeiweiZhang1 wants to merge 7 commits into
Open
Conversation
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com>
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com>
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com> # Conflicts: # auto_round/compressors/entry.py # docs/step_by_step.md # docs/step_by_step_CN.md
for more information, see https://pre-commit.ci
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com>
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
WeiweiZhang1
requested review from
n1ck-guo and
wenhuach21
and removed request for
wenhuach21
August 7, 2026 08:03
# Conflicts: # test/unit/test_cpu/algorithms/test_awq.py
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
wenhuach21
reviewed
Aug 11, 2026
| --model meta-llama/Llama-3.1-8B-Instruct \ | ||
| --scheme INT8 \ | ||
| --algorithm awq,rtn \ | ||
| --nsamples 256 \ |
Contributor
There was a problem hiding this comment.
Always use the default values unless there is a specific reason to override them.
wenhuach21
reviewed
Aug 11, 2026
|
|
||
| ar = AutoRound( | ||
| "Qwen/Qwen3-0.6B", | ||
| "meta-llama/Llama-3.1-8B-Instruct", |
wenhuach21
reviewed
Aug 11, 2026
| "meta-llama/Llama-3.1-8B-Instruct", | ||
| scheme="INT8", | ||
| alg_configs=AWQConfig(), | ||
| alg_configs=[AWQConfig(apply_clip=True), RTNConfig(disable_opt_rtn=True)], |
Contributor
There was a problem hiding this comment.
why not using alg_config="awq"
Contributor
|
What's the bug? If the bug affects accuracy, please update the accuracy results accordingly. If there are currently no accuracy results, please add some in this PR or a follow-up PR. This will make it easier for users to decide which algorithm best fits their needs. It would also be helpful to include the quantization cost. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Description
refine awq alg, add smooth seqlen, add skip_moe option, add ignore_layers config support for awq mapping, logging bugfix, refine docs
Type of Change
Bug fix
Related Issues
Fixes or relates to #
Checklist Before Submitting
/azp run Unit-Test-CUDA-AutoRound.