Master added Animate3D, negative_prompt, and context_size after this
branch diverged. The old suite did not exercise those paths, and Kokoros
no longer implemented the generated service trait.
Extend binary conformance across the tunnel owner and peer relay. Allow
long development versions so rebased binaries can register in PostgreSQL.
Clear the security findings introduced by the branch's new code.
Assisted-by: Codex:GPT-5 [apply_patch] [exec_command]
Use a regular (non-editable) pip/uv install so the package lands in the
venv site-packages. An editable finder records the builder source path,
which breaks after the backend is copied out of the image (#9162).
Adds a regression test (scripts/build/vllm-omni-install_test.sh) that
verifies imports survive relocation with a regular install and fail with
an editable install.
Supersedes #12040 (DCO not signed by contributor).
Assisted-by: MAKI:regolo/glm5.2
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Add a video_lora_dir model option that passes lora_dir as a model-load
extra to the vllm.cpp engine. The engine uses it to resolve
<lora:name:strength> prompt tags at request time, loading the safetensors
LoRA factors and applying per-request deltas without touching base weights
(row ROAD-V1-LORA-RUNTIME).
This is distinct from the existing load-time lora_path/lora_strength fusion
(ROAD-V1-DIT-LORA), which bakes deltas into the DiT weights at load. Both
mechanisms coexist: load-time adapters are always active, while prompt-tag
adapters are selected per request.
The prompt passes through verbatim — the engine strips the tags internally.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:regolo/glm5.2 [maki]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* fix(vulkan): preserve host ICD discovery for packaged backends
Add bundled Mesa manifests through VK_ADD_DRIVER_FILES instead of replacing the system driver list. Merge inherited and model-specific additive paths while preserving explicit operator overrides, with regression coverage.
Assisted-by: Codex:gpt-5 golangci-lint
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(3d): add Kimodo CPU and Vulkan animation backend
Introduce a distinct animation capability and model-described 3D operations, with a typed /3d/animate API, RPC transport, distributed media staging, permissions, and tracing.
Add a persistent kimodo.cpp adapter, skeleton GLB export, CPU/Vulkan packages, model and backend galleries, importer support, CI builds, and documentation. Adapt Studio inputs to each model and provide real-time skeleton playback, seeking, and history.
Cover backend validation, packaging, API behavior, importer inventories, distributed staging, and Studio workflows. Validate real-model CPU/Vulkan generation and deploy the integration to the local QA instance.
Assisted-by: Codex:gpt-5 golangci-lint
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(kimodocpp): adopt monolithic encoders and resident inference
Update upstream for resident weights, packed execution paths, and cached motion graphs. Default to all 32 text layers while retaining configurable streaming and legacy bundle support.
Use monolithic Q8_0 encoders by default and offer all six published quantizations through the gallery and importer. Refresh pinned hashes, tests, and documentation; remove the obsolete thread patch and ensure cached source checkouts follow the upstream pin.
Validated CPU and Vulkan generation, lower-bit streaming, gallery/importer suites, packaging, lint, and cold/warm Studio generation on localai-dev.
Assisted-by: Codex:gpt-5 golangci-lint
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
feat(vllm-cpp): wire lora_adapters/lora_scales into DiT load-time fusion
The vllm-cpp video backend now converts the standard LocalAI
lora_adapters/lora_scales config fields into indexed lora_path/
lora_strength extras pairs that vllm.cpp's ResolveDitLoraSpecs
consumes (row ROAD-V1-DIT-LORA).
The singular lora_adapter/lora_scale fields are folded in as the
first adapter. Relative paths resolve against the model directory.
Strength defaults to 1.0 when no scale is given. Adapters are fused
into DiT weights at load, so they are always loaded — no per-request
activation in this path.
Six unit tests cover the buildLoraExtras helper.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:regolo/glm5.2 [TOOL]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The CUDA 13 profile resolves PyTorch 2.14. Its headers cannot build the
current FlashAttention source release under C++17, so the full backend
matrix cannot publish the image.
Leave FlashAttention optional on CUDA 13. The backend already retries
model loading with SDPA when FlashAttention is unavailable.
Assisted-by: Codex:gpt-5
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update TheTom/llama-cpp-turboquant
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(turboquant): follow renamed RPC server target
The pinned TurboQuant fork now exposes the RPC server as
ggml-rpc-server. Build that target and copy its renamed artifact while
preserving LocalAI's packaged turboquant-rpc-server name.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update leejet/stable-diffusion.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(stablediffusion): use effective video frame rate
Capture the frame rate selected by stable-diffusion.cpp and use it when muxing the generated frames. This keeps video timing aligned with upstream model-specific adjustments.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update ggml-org/llama.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(llama-cpp): disable PCH for SYCL builds
IntelLLVM cannot bundle the precompiled headers introduced by the latest
llama.cpp update. Disable PCH for both SYCL variants while retaining it
for the other backends.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
