Skip to content

chore: ⬆️ Update ggml-org/llama.cpp to f9e832c10e9444cb168ddcb579cc62c154f3068b - #11329

Open
localai-bot wants to merge 1 commit into
mudler:masterfrom
ci-forks:update/LLAMA_VERSION
Open

chore: ⬆️ Update ggml-org/llama.cpp to f9e832c10e9444cb168ddcb579cc62c154f3068b#11329
localai-bot wants to merge 1 commit into
mudler:masterfrom
ci-forks:update/LLAMA_VERSION

Conversation

@localai-bot

@localai-bot localai-bot commented Aug 3, 2026

Copy link
Copy Markdown
Collaborator

@localai-bot
localai-bot force-pushed the update/LLAMA_VERSION branch from 32b8387 to e91a9ac Compare August 4, 2026 20:34
@localai-bot localai-bot changed the title chore: ⬆️ Update ggml-org/llama.cpp to fe2adf0e722f30f5295fdec8a0f1dc788f7498bc chore: ⬆️ Update ggml-org/llama.cpp to 4308a4f035791f58ae111f56c39dac598bf476be Aug 4, 2026
@mudler

mudler commented Aug 4, 2026

Copy link
Copy Markdown
Owner

@localai-org-maint-bot fix this

@localai-org-maint-bot

Copy link
Copy Markdown
Collaborator

Fixed and pushed in 3b1d05109. The llama.cpp gRPC wrapper now calls the new eval_llama_cmpl_schema signature in both completion paths while preserving the legacy params_from_json_cmpl fallback. The completed lint, Linux/Apple tests, llama.cpp smoke, Darwin backend build, and current CPU/Vulkan backend jobs are green; the remaining backend matrix jobs are still running.

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@localai-bot
localai-bot force-pushed the update/LLAMA_VERSION branch from 3b1d051 to d2624d3 Compare August 5, 2026 22:25
@localai-bot localai-bot changed the title chore: ⬆️ Update ggml-org/llama.cpp to 4308a4f035791f58ae111f56c39dac598bf476be chore: ⬆️ Update ggml-org/llama.cpp to f9e832c10e9444cb168ddcb579cc62c154f3068b Aug 5, 2026
@mudler

mudler commented Aug 6, 2026

Copy link
Copy Markdown
Owner

@localai-org-maint-bot check again failures

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants