feat(cuda): add LLamaSharp.Backend.Cuda13 packages - #1441
Open
modelpath-dev wants to merge 3 commits into
Open
modelpath-dev wants to merge 3 commits into
modelpath-dev wants to merge 3 commits into
Conversation
Extend the cublas matrix and Gather Binaries layout so a Compile run can produce cu13.0.0 artifacts next to cu12.4.0 without changing the managed loader or NuGet packages yet.
Teach NativeLibraryWithCuda to try major 13 when SkipCheck is on or the detected major is 13, and cover the path order with unit tests. Binaries and NuGet packages stay out of this change.
Ship the Cuda13 nuspecs, Runtime.targets copy rules for cu13.0.0 deps, and the README/QuickStart package mentions. Safe to land after binaries exist and the nuget ownership issue is resolved.
modelpath-dev
force-pushed
the
feat/1360-cuda13-nuget
branch
from
September 26, 2026 11:56
2be9259 to
05a11e2
Compare
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Part 3 of the CUDA 13 split for #1360. Ships the Backend.Cuda13 nuspecs, Runtime.targets copy rules for
cu13.0.0, and package docs. Hold this until the NuGet ownership issue Martin mentioned is resolved and cuda13 binaries exist from part 1.Depends on #1440.
Scope
LLama/runtimes/build/LLamaSharp.Backend.Cuda13*.nuspecLLama/LLamaSharp.Runtime.targetscopy-to-output links forcu13.0.0→cuda13README.md,docs/QuickStart.mdpackage mentionsOut of scope: compile workflow and
NativeLibraryWithCuda(parts 1 and 2).Tradeoffs
Runtime.targetssits with the NuGet packaging change, not the loader, because it is copy-to-output packaging for deps, notPrepare()probe logic.Blast Radius
Adds new packages and optional copy rules gated on
Exists(...). Existing Cuda12 packages and paths are untouched. Publishing still waits on package ownership.Verification