[Feature] Support vision module w8a8 inference #2308
Conversation
This file contains 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
Conflicts: lmdeploy/lite/apis/calibrate.py lmdeploy/pytorch/configurations/internvl.py
AllentDan
changed the title
Closed
lvhan028
reviewed
Sep 5, 2024
| @@ -342,7 +352,8 @@ def calib_search_scale(parser): | |||
|
|
|||
| return parser.add_argument( | |||
| '--search-scale', | |||
| type=bool, | |||
| action='store_true', | |||
There was a problem hiding this comment.
Is search-scale time consuming?
There was a problem hiding this comment.
Yes, it is time-consuming. By default, it is False.
lvhan028
reviewed
Sep 5, 2024
| """Add argument calib_image to parser.""" | ||
|
|
||
| return parser.add_argument( | ||
| '--calib-image', |
|
@AllentDan @irexyc @RunningLeon |
|
Accuracy on MMStar
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Running w8a8 for vision module and awq for llm.
Running w8a8 for both llm and vision module.
Note
--tpis not supported since the triton kernel can not get the right stream when using accelerate to dispatch modules.