Skip to content

Bump DiffusionGemma #24423 pin to c3fb9724 (Add tool calling)#32

Merged
danielhanchen merged 1 commit into
masterfrom
bump-diffusiongemma-tools-pin
Jul 8, 2026
Merged

Bump DiffusionGemma #24423 pin to c3fb9724 (Add tool calling)#32
danielhanchen merged 1 commit into
masterfrom
bump-diffusiongemma-tools-pin

Conversation

@danielhanchen

Copy link
Copy Markdown
Member

Bump the DiffusionGemma pin (ggml-org#24423) from 1d2faac to c3fb9724.

Why

The current pin (1d2faac, "Fix merge conflicts", 2026-07-03) is one commit behind c3fb9724 ("Add tool calling", 2026-07-04), which is the head of ggml-org#24423. That commit adds the three lines that let the visual server read tools from the request:

if (req.contains("tools")) {
    inputs.tools = common_chat_tools_parse_oaicompat(req.at("tools"));
}

Without it the shipped llama-diffusion-gemma-visual-server never renders the caller's tools into the chat template, so DiffusionGemma cannot produce schema-correct tool calls. This is the binary half of the DiffusionGemma tool-calling path that unslothai/unsloth#6851 and unslothai/unsloth-zoo#864 depend on.

Verification

Built c3fb9724 from source (single-arch CUDA sm_100) and ran it under Studio with unsloth/diffusiongemma-26B-A4B-it-GGUF (Q4_K_M):

  • Before (pinned 1d2faac): a plain OpenAI tools request returned "I do not have access to ... tools" (the model never saw the tool).
  • After (c3fb9724): the same request returns a structured tool_calls array, get_weather(location="San Francisco").
  • tool_choice: "none" correctly suppresses the tool.

Plain chat and the diffusion visualization are unchanged.

Lint: the new URL matches the pr-set schema and c3fb9724 is the current head of ggml-org#24423.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: a6bff50ef2

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

],
"prs": [
"https://github.com/ggml-org/llama.cpp/pull/24423/commits/1d2faac2d8248c3d5df999712c42fe0fc72e7f07",
"https://github.com/ggml-org/llama.cpp/pull/24423/commits/c3fb97241295c196e09b783e705e84b96cd1bd74",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Pin a commit that ignores tool_choice

This updated pin pulls in c3fb972, whose only tool-calling change reads req["tools"] into the chat-template inputs but never reads tool_choice. For OpenAI-compatible requests that include tools while setting tool_choice: "none", the diffusion visual server still exposes those tools to the model, so callers cannot reliably suppress tool calls in the same way the regular server does; please pin a follow-up that handles tool_choice or avoid advertising this as the tool-calling fix until that path is covered.

Useful? React with 👍 / 👎.

],
"prs": [
"https://github.com/ggml-org/llama.cpp/pull/24423/commits/1d2faac2d8248c3d5df999712c42fe0fc72e7f07",
"https://github.com/ggml-org/llama.cpp/pull/24423/commits/c3fb97241295c196e09b783e705e84b96cd1bd74",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Preserve tool-call grammar from the pinned commit

The pinned c3fb972 path only uses common_chat_templates_apply(...).prompt after adding inputs.tools; it discards the grammar and grammar_lazy that common_chat_templates_apply returns and that tools/server/server-common.cpp forwards for tool requests. For tools with required fields, enums, or numeric schemas, the visual server can now render the tools but still samples unconstrained text, so callers can receive malformed or out-of-schema tool calls instead of the schema-correct calls expected from OpenAI-compatible tool use.

Useful? React with 👍 / 👎.

@danielhanchen danielhanchen merged commit e461932 into master Jul 8, 2026
2 checks passed
@danielhanchen danielhanchen deleted the bump-diffusiongemma-tools-pin branch July 8, 2026 02:49
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.

2 participants