[Metax] support set 'dense_quant_type' to wint4 when using ERNIE model #4879
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! |
StareAtYou
force-pushed
the
develop
branch
4 times, most recently
from
3a30005 to
fb4cc9e
Compare
yuanlehome
requested changes
Nov 10, 2025
| quant_config_name = "mix_quant" | ||
|
|
||
| if current_platform.is_maca(): | ||
| metax_dense_quant_type = os.getenv("FD_METAX_DENSE_QUANT_TYPE") |
Collaborator
There was a problem hiding this comment.
添加环境变量需要统一在envs.py里注册，禁止私自添加env。尽管如此，针对这里的case，也不建议通过这种环境变量的方式来控制 dense_quant_type
Collaborator
There was a problem hiding this comment.
模型的config.json里是可以配置moe_quant_type和dense_quant_type的
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Outdated suggestions cannot be applied.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.
Motivation
1、need to support wint4 quantization on the maca platform
2、when enabling wint4 quantization mode on the maca platform, the attention quantization method can be wint4
Modifications
1、adpat wint4 quantization on the maca platform
2、support switching the attention quantization mode to wint4 on the maca platform
Usage or Command
Accuracy Tests
Checklist
[FDConfig],[APIServer],[Engine],[Scheduler],[PD Disaggregation],[Executor],[Graph Optimization],[Speculative Decoding],[RL],[Models],[Quantization],[Loader],[OP],[KVCache],[DataProcessor],[BugFix],[Docs],[CI],[Optimization],[Feature],[Benchmark],[Others],[XPU],[HPU],[GCU],[DCU],[Iluvatar],[Metax]]pre-commitbefore commit.releasebranch, make sure the PR has been submitted to thedevelopbranch, then cherry-pick it to thereleasebranch with the[Cherry-Pick]PR tag.