Skip to content

Conversation

@Edwardf0t1
Copy link
Contributor

@Edwardf0t1 Edwardf0t1 commented Dec 23, 2025

What does this PR do?

Type of change: Bug fix

Overview: Patch DeepSeek V3 config to add missing qk_head_dim attribute, which is needed for Kimi-K2-Thinking.

Usage

python hf_ptq.py --pyt_ckpt_path <Kimi-K2-Thinking_path> --qformat nvfp4 --export_path <quantized_ckpt> --kv_cache_qformat none --calib_size 64 --trust_remote_code --dataset cnn_dailymail

Testing

Before your PR is "Ready for review"

  • Make sure you read and follow Contributor guidelines and your commits are signed.
  • Is this change backward compatible?: Yes/No
  • Did you write any new necessary tests?: Yes/No
  • Did you add or update any necessary documentation?: Yes/No
  • Did you update Changelog?: Yes/No

Additional Information

Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
@codecov
Copy link

codecov bot commented Dec 23, 2025

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.69%. Comparing base (3350b0a) to head (381ac9d).

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #723   +/-   ##
=======================================
  Coverage   74.69%   74.69%           
=======================================
  Files         192      192           
  Lines       18946    18946           
=======================================
  Hits        14152    14152           
  Misses       4794     4794           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants