Repository navigation
feat: EXPKITS-1441 add optional MLWL inference backend - #169
Merged
Conversation
Szendvics
added this pull request to stack #175
October 22, 2026 10:10
Szendvics
removed this pull request from stack #175
October 22, 2026 11:44
Szendvics
added this pull request to stack #177
October 22, 2026 11:44
Szendvics
force-pushed
the
feature/EXPKITS-1441-public-mlwl-backend-01a162dd
branch
from
October 22, 2026 12:00
fe15b16 to
75c68a4
Compare
Szendvics
removed this pull request from stack #177
October 22, 2026 12:20
Szendvics
added this pull request to stack #179
October 22, 2026 12:20
Szendvics
removed this pull request from stack #179
October 22, 2026 13:14
Szendvics
force-pushed
the
feature/EXPKITS-1441-public-mlwl-backend-01a162dd
branch
from
October 22, 2026 13:15
ec0930e to
344582f
Compare
Szendvics
changed the base branch from
main
to
feature/EXPKITS-1441-mlwl-release-packaging-01a11fdd
October 22, 2026 13:15
Szendvics
added this pull request to stack #183
October 22, 2026 13:15
Szendvics
removed this pull request from stack #183
October 22, 2026 13:44
Szendvics
force-pushed
the
feature/EXPKITS-1441-public-mlwl-backend-01a162dd
branch
2 times, most recently
from
October 22, 2026 13:45
3cf65a1 to
1f84bf6
Compare
Szendvics
merged commit Oct 22, 2026
1f84bf6
into
feature/EXPKITS-1441-mlwl-release-packaging-01a11fdd
Szendvics
force-pushed
the
feature/EXPKITS-1441-mlwl-release-packaging-01a11fdd
branch
from
October 22, 2026 13:45
1172166 to
8474427
Compare
Szendvics
deleted the
feature/EXPKITS-1441-public-mlwl-backend-01a162dd
branch
October 22, 2026 13:45
Szendvics
restored the
feature/EXPKITS-1441-public-mlwl-backend-01a162dd
branch
October 22, 2026 13:48
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
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.
Goal
Run VGF models through MLWL using the same inference interface as ONNX and ExecuTorch.
Change
Add the optional MLWL 0.11.0 backend, tensor validation and pinned dependency installer. Disabled by default.
Package the runtime and original notices in release, deployment and Debian outputs. Archives and Debian packages also carry a checksum receipt. Validate the payload and keep VGF binaries out of source and runtime packages.
Testing
Release-helper and build-wrapper tests pass. Native x64/ARM64 package builds and MLWL CPU inference passed before restacking. Full builds and inference have not been repeated on this head.