Upgrade llama.cpp to b10333 and CUDA to 13.3 - #384
Merged
Conversation
Jimver/cuda-toolkit v0.2.36 (PR #445) added toolkit mappings for CUDA 13.3.0/13.3.1, and cuda-toolkit-13-3 is now available in NVIDIA's RHEL8 dnf repo, so both the Linux (build_cuda_linux.sh) and Windows (publish.yml Jimver job) pins move to 13.3.1. The pom.xml classifier stays cuda13-linux-x86-64 (major-version only, per the documented runbook).
Single-step bump (76 KiB / 6 commits, under the 100 KiB chunking
threshold). Diff review: purely additive common_params::server_tools_runtime
field + --tools-runtime CLI flag, an opt-in Docker-backed built-in-tools
runtime (server-tools.{h,cpp}, not referenced by jllama.cpp directly),
and internal CUDA rope-kernel work. No project source changes required.
All 6 patches re-verified against a clean b10333 checkout (sequential
git apply). Full local build + ctest: 482/482 passing.
bernardladenthin
had a problem deploying
to
startgate
August 9, 2026 22:29 — with 
GitHub Actions
Error
GitHub Actions
Error
bernardladenthin
had a problem deploying
to
maven-central
August 9, 2026 22:29 — with
GitHub Actions
Failure
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
maven-central
August 9, 2026 22:29 — with
GitHub Actions
Failure
GitHub Actions
Failure
Review Complete ✅This PR successfully upgrades llama.cpp from b10327 to b10333 and CUDA from 13.2 to 13.3. Version Pin Consistency: All 8 version references updated correctly
Patch Validation:
Code Quality: Excellent - documentation is precise and complete with no stale references Recommendation: ✅ Approved for merge |
|
6 tasks
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
2 participants
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.
Summary
Test plan
Related issues / PRs
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdSECURITY.md)https://claude.ai/code/session_01CtT7KLNmC8gEoDS1EiGGwD