chore: bump llama.cpp to b9501

[ilopezluna]

No description provided.

[gemini-code-assist]

Code Review

This pull request updates the llama.cpp server version from b8967 to b9501, modifying the .versions file, Dockerfile, and the vendor subproject commit. There are no review comments, and 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.

[sourcery-ai]

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="3-6" />
<code_context>

 ARG GO_VERSION=1.25
-ARG LLAMA_SERVER_VERSION=b8967
+ARG LLAMA_SERVER_VERSION=b9501
 ARG LLAMA_SERVER_VARIANT=cpu
-ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b8967
+ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9501

 ARG VERSION=dev
</code_context>
<issue_to_address>
**suggestion:** Avoid duplicating the version string by deriving LLAMA_UPSTREAM_IMAGE from LLAMA_SERVER_VERSION.

`b9501` is currently duplicated in both `LLAMA_SERVER_VERSION` and `LLAMA_UPSTREAM_IMAGE`, which makes version bumps error-prone. Instead, compose `LLAMA_UPSTREAM_IMAGE` from `LLAMA_SERVER_VERSION`, e.g.:

```dockerfile
ARG LLAMA_SERVER_VERSION=b9501
ARG LLAMA_SERVER_VARIANT=cpu
ARG LLAMA_UPSTREAM_BASE=ghcr.io/ggml-org/llama.cpp
ARG LLAMA_UPSTREAM_IMAGE=${LLAMA_UPSTREAM_BASE}:server-vulkan-${LLAMA_SERVER_VERSION}
```

This keeps the version in a single place and avoids mismatches on future updates.

```suggestion
ARG GO_VERSION=1.25
ARG LLAMA_SERVER_VERSION=b9501
ARG LLAMA_SERVER_VARIANT=cpu
ARG LLAMA_UPSTREAM_BASE=ghcr.io/ggml-org/llama.cpp
ARG LLAMA_UPSTREAM_IMAGE=${LLAMA_UPSTREAM_BASE}:server-vulkan-${LLAMA_SERVER_VERSION}
```
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion: Avoid duplicating the version string by deriving LLAMA_UPSTREAM_IMAGE from LLAMA_SERVER_VERSION.

b9501 is currently duplicated in both LLAMA_SERVER_VERSION and LLAMA_UPSTREAM_IMAGE, which makes version bumps error-prone. Instead, compose LLAMA_UPSTREAM_IMAGE from LLAMA_SERVER_VERSION, e.g.:

ARG LLAMA_SERVER_VERSION=b9501
ARG LLAMA_SERVER_VARIANT=cpu
ARG LLAMA_UPSTREAM_BASE=ghcr.io/ggml-org/llama.cpp
ARG LLAMA_UPSTREAM_IMAGE=${LLAMA_UPSTREAM_BASE}:server-vulkan-${LLAMA_SERVER_VERSION}

This keeps the version in a single place and avoids mismatches on future updates.

Suggested change

	ARG GO_VERSION=1.25
	ARG LLAMA_SERVER_VERSION=b8967
	ARG LLAMA_SERVER_VERSION=b9501
	ARG LLAMA_SERVER_VARIANT=cpu
	ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b8967
	ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9501
	ARG GO_VERSION=1.25
	ARG LLAMA_SERVER_VERSION=b9501
	ARG LLAMA_SERVER_VARIANT=cpu
	ARG LLAMA_UPSTREAM_BASE=ghcr.io/ggml-org/llama.cpp
	ARG LLAMA_UPSTREAM_IMAGE=${LLAMA_UPSTREAM_BASE}:server-vulkan-${LLAMA_SERVER_VERSION}

[ericcurtin]

We should do something about this file, manually editing this really isn't great