Bump llamacpp to b9859#995
Conversation
There was a problem hiding this comment.
Code Review
This pull request updates the LLAMA_SERVER_VERSION to b9859 in the .versions file and the Dockerfile, and bumps the llama.cpp vendor subproject commit to 4fc4ec5541b243957ae5099edb67372f8f3b550e. I have no feedback to provide.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
There was a problem hiding this comment.
Hey - I've found 1 issue
Prompt for AI Agents
Please address the comments from this code review:
## Individual Comments
### Comment 1
<location path="Dockerfile" line_range="4-6" />
<code_context>
ARG GO_VERSION=1.25
-ARG LLAMA_SERVER_VERSION=b9592
+ARG LLAMA_SERVER_VERSION=b9859
ARG LLAMA_SERVER_VARIANT=cpu
-ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9592
+ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9859
ARG VERSION=dev
</code_context>
<issue_to_address>
**suggestion:** Avoid duplicating the llama.cpp version string to reduce risk of future drift.
LLAMA_SERVER_VERSION and LLAMA_UPSTREAM_IMAGE both embed `b9859`. Please derive LLAMA_UPSTREAM_IMAGE from LLAMA_SERVER_VERSION (e.g., via build arg or build-time substitution) so version bumps only require a single update and can’t drift out of sync.
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
| ARG LLAMA_SERVER_VERSION=b9859 | ||
| ARG LLAMA_SERVER_VARIANT=cpu | ||
| ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9592 | ||
| ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9859 |
There was a problem hiding this comment.
suggestion: Avoid duplicating the llama.cpp version string to reduce risk of future drift.
LLAMA_SERVER_VERSION and LLAMA_UPSTREAM_IMAGE both embed b9859. Please derive LLAMA_UPSTREAM_IMAGE from LLAMA_SERVER_VERSION (e.g., via build arg or build-time substitution) so version bumps only require a single update and can’t drift out of sync.
No description provided.