Offer intermediate quantizations alongside the existing Q4 and Q8 builds.
Keep the shared BF16 projector and llama.cpp MTP configuration. Pin new
files to a Hugging Face revision and document explicit variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 73c3b16d12, mudler/LocalAI#12592)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer intermediate quantizations between the existing Q4 and Q8 builds.
Pin both to the same publisher revision to preserve the step-576 merge.
Document explicit variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit e78c44dc7b, mudler/LocalAI#12591)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Fill the gap between the existing Q4 and Q8 builds with the
publisher's Q5_K_M and Q6_K GGUF files. Preserve the runtime settings
and license notice, and document explicit variant installation.
Assisted-by: Codex:gpt-6
(cherry picked from commit 3b73ecd1e2, mudler/LocalAI#12589)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The Qwopus 3.5 9B Coder MTP projector URL returns 404. Use the
publisher's mmproj-F32.gguf, which has the same SHA256, and pin
all downloads to the verified repository revision.
Offer Q6_K and Q8_0 variants alongside Q4_K_M and document explicit
selection. Keep the existing MTP and chat-template settings.
Assisted-by: Codex:gpt-6
(cherry picked from commit 01c5e044f2, mudler/LocalAI#12586)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add JetBrains Q4_K_M and Q8_0 GGUF builds for llama.cpp, with
variant selection and installation documentation. Pin both downloads
and verify their SHA256 values against LFS metadata and HTTP headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit a5accc7488, mudler/LocalAI#12573)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q8_0 and BF16 builds for text embeddings through llama.cpp.
Document installation and retrieval task prefixes.
Assisted-by: Codex:gpt-6
(cherry picked from commit b166f881e9, mudler/LocalAI#12565)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add the mixed IQ2 GGUF with its F16 vision projector for llama.cpp.
Pin both downloads and cross-check SHA256 values against HF LFS metadata.
Document installation and the default context size.
Assisted-by: Codex:gpt-6
(cherry picked from commit 3657d221a0, mudler/LocalAI#12564)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add the Japanese Spark-X2.5-4B adaptation in Q4_K_M and Q8_0.
Pin both downloads and document variant selection and output budgets.
Assisted-by: Codex:gpt-6
(cherry picked from commit 592a913442, mudler/LocalAI#12563)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q8_0 builds with the BF16 vision projector for llama.cpp.
Pin all three assets to a Hugging Face revision and document installation.
Assisted-by: Codex:gpt-6
(cherry picked from commit 215ec2f0f9, mudler/LocalAI#12561)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Q4_K_M and Q8_0 builds of the Qwen3.5 tool-routing fine-tune.
Keep the entries text-only because the quantization repository does
not publish a vision projector. Pin downloads and document selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 98cad4a19f, mudler/LocalAI#12559)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q6_K builds with the BF16 vision projector.
Pin all files to a verified Hugging Face revision and document usage.
Assisted-by: Codex:gpt-6
(cherry picked from commit 689aca7f03, mudler/LocalAI#12552)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q8_0 builds with the F16 vision projector. Pin the
assets and document the prompts needed for adaptive visual reasoning.
Assisted-by: Codex:gpt-6
(cherry picked from commit 8c64079b01, mudler/LocalAI#12547)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q8_0 builds with the F16 vision projector for document
visual question answering. Pin the assets and document the external
agent loop needed to reproduce the publisher's agentic results.
Assisted-by: Codex:gpt-6
(cherry picked from commit 50f2715967, mudler/LocalAI#12545)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Fill the quantization gap between the existing Q4 and Q8 builds. Pin both downloads to the same publisher revision and verify SHA256 values against LFS metadata and x-linked-etag headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit 1c17d6fe9d, mudler/LocalAI#12543)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add the published four-shard UD-Q4_K_XL build for llama.cpp with
revision-pinned downloads and verified SHA256 checksums. Document
installation, download size, text-only input, and sampling defaults.
Assisted-by: Codex:gpt-6
(cherry picked from commit e32d0f50de, mudler/LocalAI#12542)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q8_0 GGUF builds for screenshot interpretation and GUI
planning with llama.cpp. Include the F16 vision projector in both builds
and document installation and the separate action executor requirement.
Pin all downloads and verify SHA256 values against Hugging Face LFS
metadata and download headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit c4273485d1, mudler/LocalAI#12541)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Q4_K_M and Q6_K builds for character roleplay with llama.cpp.
Pin downloads and document explicit variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 2aaae6cfd3, mudler/LocalAI#12523)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Q4_K_M and Q8_0 builds with the matching vision projector.
Pin downloads and verify their SHA256 against Hugging Face metadata
and response headers. Document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 0e8ebcde37, mudler/LocalAI#12516)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add Q4_K_M and Q8_0 builds with the matching vision projector for
single-step screenshot grounding on Kayak interfaces.
Assisted-by: Codex:gpt-6-astra
(cherry picked from commit 2f54c3216a, mudler/LocalAI#12513)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add official Q4_K_M and Q8_0 builds with pinned downloads and verified
SHA256 values. Document installation and text translation prompts.
Assisted-by: Codex:gpt-6
(cherry picked from commit e50820d9d0, mudler/LocalAI#12512)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Offer Q4_K_M and Q8_0 builds for cited research reports from supplied
literature excerpts. Use the embedded Qwen3 template and document the
upstream prompt. Pin both downloads and cross-check their SHA256 values
against Hugging Face LFS metadata and download headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit b14169ac2a, mudler/LocalAI#12509)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add three llama.cpp quantizations with the matching vision projector,
MTP decoding, and installation examples. Pin downloads to one Hugging
Face revision and verify SHA256 values against LFS metadata and headers.
Assisted-by: Codex:gpt-6
(cherry picked from commit b5f4a2f958, mudler/LocalAI#12498)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
FLAC normalization renames the backend's WAV destination. The next
request then reuses that apparently vacant path and replaces the first
recording when normalization runs again.
Give each request a UUID filename, and test that successive FLAC outputs
retain distinct paths and their original bytes.
Addresses the overwrite report in #12633. Reference-audio input remains
outside this fix.
Assisted-by: Codex:gpt-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
Pin the merge of LocalRecall #58 to include the PostgreSQL raw-vector
API and its reviewed client fixes. Keep existing text integration unchanged.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* feat(launcher): package a Linux AppImage
Ship the existing Fyne launcher as an additive release asset without
bundling the server or changing its runtime downloader.
Pin packaging tools and the type-2 runtime, preserve the caller
environment, and document the native amd64 graphics requirements.
Validate packaging contracts and wire extraction smoke checks into CI.
Assisted-by: Codex:gpt-5
* fix(launcher): harden AppImage release checks
PR builds must not receive repository write credentials. Isolate uploads
in a gated job that consumes the tested artifact without checkout.
Keep the existing release check and dependency on GoReleaser.
A surviving process does not prove that the UI event loop works.
Require observable startup progress, reject initialization errors, and
bound termination. Document the remaining limits without changing the
launcher application. Add permission and smoke failure regressions.
Assisted-by: nib:unknown
* fix(launcher): install file for AppImage builds
appimagetool fails after Go compilation when file is missing. Install
it explicitly in CI and document the local build dependency. Check for
it before compilation and cover the missing-command failure in tests.
Assisted-by: nib:unknown
---------
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): preserve chat session state
Newer llama.cpp parsers return template state outside the request JSON.
Pass that state to both inference tasks and response readers so grammar,
tool calls, and reasoning remain available in both chat paths.
Detect the parser API during preparation to preserve older fork builds.
Assisted-by: Codex:gpt-6
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
* test(omnivoice): expose ignored duration controls
Compile the real wrapper with a model-free engine fixture. Four failing
assertions expose ignored duration, postprocessing, and validation.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(omnivoice): add bounded duration controls
Validate request controls before reference reads or native output.
Preserve engine defaults when controls are omitted. Bound forced
single-shot duration to 30 seconds as wrapper resource policy.
Exercise the real native boundary, streaming rejection, and defaults
with synthetic PCM. Document quantization and postprocessing limits.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(omnivoice): require fixture-free ordinary tests
Expose the ordinary suite regression before isolating native fixtures.
Require selected native tests to reject a missing fixture explicitly.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(omnivoice): isolate native fixture tests
Ordinary Go tests must run without a compiled native fixture.
Select fixture specs explicitly in the dedicated gate while keeping
parser tests ordinary and native checks mandatory.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Aliases have no model file, so guessing attempts to parse the models
directory. Skip that work while retaining the context fallback and
normal alias validation.
Use a private call-local parser dependency to verify operation counts
without a mutable global hook. Cover concrete guessing, defaults,
alias validation, and resolved target equivalence.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Exact configured requests need no loose-file enumeration. Reuse the
synchronized config lookup without adding a cache. Misses retain regex
discovery and raw-weight fallback with ALWAYS_INCLUDE.
Keep general listing and bearer discovery unchanged. Preserve request
validation, alias resolution, disabled-target checks, and model access.
Record diagnostics only for work performed.
Assisted-by: nib:gpt-6-astra
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
test: satisfy lint checks for upscale and diagnostics
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
