How are the quantization parameters of block_ap passed to the e2e-qp stage?
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 35/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Start at the reported load_checkpoint_in_model(...) call and trace how the block_ap checkpoint is handed to the e2e-qp stage. Compare which quantization scales and zero points are expected to be consumed; done means determining whether the "were not used" messages are expected and identifying the relevant checkpoint-loading behavior.
Written by the indexing model from the issue text.
Description
Thank you for your work. I noticed that when loading the model between the two stages, load_checkpoint_in_model(model, checkpoint=model_path, device_map=device_map, offload_state_dict=True), all the scales and zero points were indicated as "were not used." Is this normal?
- Dominant language
- Python
- Stars
- 351
- Forks
- 38
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from OpenGVLab/EfficientQAT
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
OpenGVLab/EfficientQAT#31 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 28/100
OpenGVLab/EfficientQAT#34 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
OpenGVLab/EfficientQAT#33 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
OpenGVLab/EfficientQAT#32 ·
-
About DatasetOpen
Difficulty 5/5 Over a week Newbie friendliness 20/100
OpenGVLab/EfficientQAT#30 ·
All issues in OpenGVLab/EfficientQAT
Similar issues
-
New InternshipOpennew_internship
Difficulty 1/5 Under an hour Newbie friendliness 70/100
-
[BUG] Reports tab: "Unban" button tooltip shows raw `{{ip}}` placeholder instead of the IP addressOpenbug javascript ui
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
bunkerity/bunkerweb#4001 · 1 comment ·
Maintainers usually reply within 1 day
-
bug
Difficulty 1/5 Under an hour Newbie friendliness 92/100
PedestrianDynamics/pyFDS-Evac#476 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
google/differential-privacy#516 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
adobe-fonts/source-serif#153 ·