-
-
Notifications
You must be signed in to change notification settings - Fork 3.9k
feat(rocm): add ROCm 7.x build support (11 rocWMMA-compatible architectures) #9230
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
Open
walcz-de
wants to merge
13
commits into
mudler:master
Choose a base branch
from
walcz-de:pr/rocm7-gfx1151-build-support
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from 3 commits
Commits
Show all changes
13 commits
Select commit
Hold shift + click to select a range
5fd709a
feat(rocm): add ROCm 7.x and gfx1151 (AMD Strix Halo / RDNA 3.5) buil…
walcz-de 022affc
fix(rocm7): correct package name, add rocWMMA headers, fix LD_LIBRARY…
walcz-de bec5ca2
feat(rocm): extend ROCm 7.x / gfx1151 support to all backends
walcz-de d6e164e
scripts: add all-backend support to sync-upstream.sh and build-rocm.sh
walcz-de 8551148
feat(rocm): support all ROCm 7.12 GPU architectures (not just gfx1151)
walcz-de 5f528de
fix(llama-cpp): always remove stale variant build dirs before make
walcz-de 76c1f98
fix(llama-cpp): remove GGML_HIP_ROCWMMA_FATTN for multi-arch fat bina…
walcz-de b2a10f1
fix(llama-cpp): restrict AMDGPU_TARGETS to rocWMMA-compatible arches
walcz-de f277282
refactor(scripts): rename image tags from gfx1151 to rocm<version>
walcz-de 1e67648
fix(Dockerfile.llama-cpp): resolve CPATH lint warning in ENV instruction
walcz-de ad3a714
feat(scripts): push to both local registries on local builds
walcz-de c1c8fa5
fix(rocm7): bundle rocm_sysdeps and hipblaslt libs in backend package
walcz-de 91c18c6
fix(Dockerfile.llama-cpp): cmake before ROCm, force-overwrite DNN con…
walcz-de File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
Oops, something went wrong.
Oops, something went wrong.
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.
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.
is this specific to a single rocm arch? this is quite restrictive and would support only one specific version, which is not really what we want here. Is there a way to support a target list, like we do in llama.cpp?
LocalAI/backend/cpp/llama-cpp/Makefile
Line 36 in 6f304d1
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.
Well it shouldn't be, but I ran into some trouble during the build so I was first narrowing it down to gfx1151 because it is one of the platforms actually benefitting from exactly the 7.12. rock. BUT that said, of course you are right and it should be for a list of AMDGPU_TARGETS. I will get on it.