-
Notifications
You must be signed in to change notification settings - Fork 88
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Driver quantize fp8 update #3715
base: ocp_to_fnuz
Are you sure you want to change the base?
Conversation
CharlieL7
commented
Dec 13, 2024
•
edited
Loading
edited
- Updates the quantization to always quantize fp8 to the OCP fp8e4m3fn type
- Removes running simplify_qdq and optimize_module during the quantization so that the ocp_to_fnuz conversion pass can work properly
- Don't merge this until FP8 OCP to FP8 FNUZ on hardware with only FP8 FNUZ support #3684 is done.
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## ocp_to_fnuz #3715 +/- ##
===============================================
+ Coverage 92.23% 92.25% +0.02%
===============================================
Files 517 517
Lines 21819 21808 -11
===============================================
- Hits 20124 20120 -4
+ Misses 1695 1688 -7 ☔ View full report in Codecov by Sentry. |
@@ -311,7 +311,6 @@ struct context | |||
value result; | |||
result["events"] = events.size(); | |||
result["streams"] = current_device->nstreams(); | |||
result["gfx_name"] = get_current_device().get_gfx_name(); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why is this removed on serialization?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I added this earlier when getting FP8 OCP in to query the gfx number from the driver. We could keep it, but it would not be used anywhere anymore.