# Contributor handoff — ggml-org/llama.cpp

> Canonical page: https://codevetter.com/unpack/llama-cpp/agent-handoff

# Contributor handoff — ggml-org/llama.cpp

Scanned commit 7ab4ee7baad2d920464cbacfad4f4b07cf111fd2 (2026-09-22). Generated by codevetter codevetter 1.12.0 on 2026-09-22.

Read AGENTS.md first — it is strict: ASCII-only, concise comments, no new test files without maintainer approval, never commit/push/PR on the user's behalf, reuse existing infra. Build with cmake -B build && cmake --build build -j; run C++ tests via ctest and server tests via tools/server/tests/tests.sh. Key files to read before editing: common/arg.cpp (params), tools/server/README-dev.md (server feature scope), docs/development/HOWTO-add-model.md (arch additions), and the pimpl of whatever you touch (server_context_impl, llama_model subclasses).
- AGENTS.md is mandatory and unusual: it forbids agents from writing PR descriptions/comments/reviewer responses, forbids git push/gh pr create entirely (project ban risk), requires 'Assisted-by:' not 'Co-authored-by:' in human-approved commits, and tells fully autonomous agents to stop and exclude llama.cpp from contribution targets. — [AGENTS.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/AGENTS.md)
- Style rules enforced by maintainers: no emdashes/unicode arrows (use ASCII '-', '->', 'x', '...'), comments are 1-2 lines max in ASD-STE100 simplified English, no hard-wrapping comments, no comment-first-then-code, and do NOT split a line mid-sentence to fit a column width. — [AGENTS.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/AGENTS.md)
- Do not add new files under tests/ without maintainer approval — reuse existing test infrastructure; test-chat links against the server-context library so server chat changes can be exercised from tests/test-chat.cpp. — [AGENTS.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/AGENTS.md) [tests/CMakeLists.txt#L163-166](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tests/CMakeLists.txt#L163-L166)
- Server feature scope is contractually bounded by tools/server/README-dev.md: in-scope = inference, chat/tool calling, API compat, multimodal, memory mgmt, Web UI needs; out-of-scope = server-side agentic loops, internal-state APIs, model-specific features; file-IO features (MCP, model save/load) must be disabled by default for security. — [tools/server/README-dev.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/README-dev.md)
- Build: cmake -B build (Release default, BUILD_SHARED_LIBS on) then cmake --build build -j produces bin/llama plus llama-* tools; LLAMA_BUILD_UI embeds the web UI; LLAMA_SUBPROCESS is off on iOS/Android/Emscripten which disables server router mode and server tools. — [CMakeLists.txt#L104-146](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/CMakeLists.txt#L104-L146) [tools/server/server-models.cpp#L1923-1924](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-models.cpp#L1923-L1924)
- Test invocation: ctest --test-dir build (label 'main' runs the core suite; 'model' needs downloaded models); server suite: cd tools/server/tests && ./tests.sh (needs PYTEST deps, spawns built server); UI: cd tools/ui && npm test (vitest+playwright). — [tests/CMakeLists.txt#L26-47](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tests/CMakeLists.txt#L26-L47) [tools/server/tests/tests.sh](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/tests/tests.sh) [tools/ui/package.json#L17-24](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/ui/package.json#L17-L24)
- Before touching CLI behavior read common/arg.cpp's common_params_parser_init — every flag is a common_arg with examples/env/handler; adding a flag means one table entry plus documentation regeneration; LLAMA_EXAMPLE_* gating controls which binaries accept the flag. — [common/arg.cpp#L77-141](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/common/arg.cpp#L77-L141) [common/arg.h](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/common/arg.h)
- Server edits: the inference core is server_context_impl inside tools/server/server-context.cpp (pimpl over server_context); slot scheduling lives in process_single_task/get_available_slot/launch_slot_with_task; decode loop is update_slots -> pre_decode/decode/post_decode; HTTP routes are registered in server.cpp not in server-context. — [tools/server/server-context.cpp#L2375-2453](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-context.cpp#L2375-L2453) [tools/server/server-context.cpp#L2793-2907](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-context.cpp#L2793-L2907) [tools/server/server.cpp#L248-306](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server.cpp#L248-L306)
- Adding a model arch requires coordinated edits across five places: conversion/<arch>.py (ModelBase.register), gguf-py/gguf/constants.py (MODEL_ARCH/MODEL_TENSORS), src/llama-arch.* (LLM_ARCH_*), src/models/<arch>.cpp (graph builder), and llama_model_mapping in src/llama-model.cpp — HOWTO-add-model.md is the canonical guide. — [docs/development/HOWTO-add-model.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/docs/development/HOWTO-add-model.md) [src/llama-model.cpp#L43-373](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/src/llama-model.cpp#L43-L373) [src/llama-arch.h](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/src/llama-arch.h)
- The chat stack has traps: llama.cpp uses its own Jinja engine in common/jinja (NOT minja — AGENTS.md explicitly warns about stale knowledge); tool-call parsers are PEG-based in common/peg-parser.cpp + common/parsers; use test-chat-peg-parser/test-jinja to validate changes. — [AGENTS.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/AGENTS.md) [common/jinja/README.md](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/common/jinja/README.md) [tests/CMakeLists.txt#L258-263](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tests/CMakeLists.txt#L258-L263)
- Concurrency model: a single decode thread runs queue_tasks.start_loop -> update_slots; HTTP handlers run on httplib threads and only communicate via queue_tasks.post + queue_results; decode yields via yield_to_queue only for metrics/slot-read tasks — never call llama_decode off the main loop. — [tools/server/server-queue.h#L14-45](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-queue.h#L14-L45) [tools/server/server-context.cpp#L2375-2380](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-context.cpp#L2375-L2380) [tools/server/server-queue.cpp#L278-316](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-queue.cpp#L278-L316)
- Known foot-guns: GGML_ABORT crashes on error paths; llama_decode errors clear entire slots; llama-server.cpp default port 8080 is slated to change to 9931; embeddings require n_batch<=n_ubatch (auto-clamped with warning); 'completion' is the legacy hidden tool — prefer server/cli paths for new work. — [tools/server/server-context.cpp#L3652-3719](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server-context.cpp#L3652-L3719) [tools/server/server.cpp#L148-152](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server.cpp#L148-L152) [tools/server/server.cpp#L514-518](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/tools/server/server.cpp#L514-L518) [app/llama.cpp#L69](https://github.com/ggml-org/llama.cpp/blob/7ab4ee7baad2d920464cbacfad4f4b07cf111fd2/app/llama.cpp#L69)

Every claim links to its cited files at the pinned commit. Citations identify source evidence; they do not establish runtime correctness. Independent CodeVetter scan — not reviewed by upstream maintainers.

## Public product links

- [CodeVetter](https://codevetter.com/)
- [Download](https://codevetter.com/download)
- [Documentation](https://codevetter.com/docs/)
- [Source](https://github.com/Codevetter/codevetter)