pengxin99 comments

Results 20 comments of


                                            pengxin99

Fix SMT Surface Sync issue with par file usage.

No need for now

Add description of the return status for vaSyncSurface()

Hi, @XinfengZhang @Jexu, have add more detail description, could you pls help to review this PR again?

Add description of the return status for vaSyncSurface()

@XinfengZhang Thanks for the comments. and I will refine this PR for below two point: > VA_STATUS_ERROR_HW_BUSY is about the HW reset , but looks could not distinguish , media...

Add description of the return status for vaSyncSurface()

> Also, please, squash commits. For this change there should be just 1 commit in the PR. @dvrogozh Thanks for your review, and have refined this PR, could pls have...

Add description of the return status for vaSyncSurface()

Hi, @dvrogozh @XinfengZhang , Can you take another look at this PR if you have time?

Add description of the return status for vaSyncSurface()

Hi, @XinfengZhang , Could you pls take another look at this PR when you have time?

av1d: improve decode DPB management

Done in this commit: https://github.com/oneapi-src/oneVPL-intel-gpu/commit/15e3bda58d52ef4c8cf2cb2f6e3c50cf9e819800

fix windows build issue with numeric_limits

Hi, @mschilling0, could you pls help to review this PR?

Implemented Flash Attention2 for Intel GPU hardware

This is excellent work!! And looking forward to using this feature in Intel Client GPUs.

how to evaluate AWQ ?

Hi, @chunniunai220ml, try with the old version like 2.6 may solve this issue: `ModuleNotFoundError: No module named 'neural_compressor.conf'`