Conversation
e212912 to
62a9d71
Compare
62a9d71 to
c956e29
Compare
|
@leejet could I get this reviewed please? Same with the windows one too |
|
+1 @leejet can you please help review this? |
|
@leejet could you review this please? |
|
I think this project needs at least one other code owner. |
…ases AMD is in the process of moving over to a brand new build system (TheRock). They have a preview release stream for it, and it includes some significant performance uplifts. To let people experiment with both stacks generate artifacts both for the stable (7.2.1) and preview (7.12) stacks. In both cases - ROCm must be installed first to use this artifact. It's intentionally not bundled because so many ISAs are included and the size of the artifact balloons to an untenable size.
c956e29 to
85c8892
Compare
|
I've rebased the branch on latest master, and also updated to current ROCm versions (7.2.1 legacy release and 7.12 preview release). |
|
The "failing checks" appear to be only relevant for containers at release. @leejet can you please review? |
At this point, it would be better for you to create a fork specifically for ROCm than to wait for the repository owner to get around to it. |
Switch over ROCm builds to artifacts both for stable and preview releases
AMD is in the process of moving over to a brand new build system (TheRock). They have a preview release stream for it, and it includes some significant performance uplifts.
To let people experiment with both stacks generate artifacts both for the stable (7.2) and preview (7.11) stacks.
In both cases - ROCm must be installed first to use this artifact. It's intentionally not bundled because so many ISAs are included and the size of the artifact balloons to an untenable size.
The new artifacts are a much more reasonable ~145MB. And a user won't end up with multiple ROCm stacks on the machine now if they use other software like llama.cpp.