mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-09-26 08:05:00 -04:00
Code Issues Packages Projects Releases Wiki Activity
8,051 Commits 222 Branches 178 Tags
fix/swagger-backend-metadata
Commit Graph
2119 Commits
Author SHA1 Message Date
localai-org-maint-botandmudler 19a66fd898 chore: ⬆️ Update ggml-org/llama.cpp to e613ef2c81bae98d59850d061ac29e6e3e88cb00 (#12157) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 22:00:45 +02:00
Richard Palethorpe 495165266f feat(kimodocpp): track usage through generic backend metadata (#12162) 
Report input tokens and frame-step output units in response metadata and
record them through the existing usage accounting pipeline. Preserve the
accounting rule and model-specific dimensions as JSON without extending
the gRPC schema for each modality.

Expose animation usage only under metadata.usage, validate counts before
recording, and document the response contract and loaded-model location.
Add coverage for transport, defaults, failures, persistence, and recording
requests once with statistics enabled or disabled.

Assisted-by: Codex:GPT-6

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-09-20 19:39:06 +01:00
localai-org-maint-botandmudler 416847e20d chore: ⬆️ Update PrismML-Eng/llama.cpp to 9a9394a895b96003ca842a6041cb28ac49a108f7 (#12114) 
⬆️ Update PrismML-Eng/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:35:49 +02:00
localai-org-maint-botandmudler 1678129e91 chore: ⬆️ Update 0xShug0/audio.cpp to a7b58a6d3d6ae4143c485266b1c6c09898ad8c72 (#12150) 
⬆️ Update 0xShug0/audio.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:32:09 +02:00
localai-org-maint-botandmudler 1678699c49 chore: ⬆️ Update mudler/vllm.cpp to ea8c83d75f461a520e41328c44bde6c949453fa6 (#12149) 
⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:31:54 +02:00
localai-org-maint-botandmudler 8ef96e692e chore: ⬆️ Update ikawrakow/ik_llama.cpp to 401a09d2f534d2eeabb0a37919ebc5a2cbc56ac6 (#12151) 
⬆️ Update ikawrakow/ik_llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:31:35 +02:00
localai-org-maint-botandmudler fbfac13ff4 chore: ⬆️ Update leejet/stable-diffusion.cpp to 1330cebae8f2ba99249df846cc0c9444fcbd4308 (#12152) 
⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:31:15 +02:00
localai-org-maint-botandmudler cdd0ad2004 chore: ⬆️ Update CrispStrobe/CrispASR to 7bd1d6062eb3d96dfb68fb240f8736399ba490c3 (#12153) 
⬆️ Update CrispStrobe/CrispASR

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-20 12:30:53 +02:00
mudler-agentandEttore Di Giacinto 6184a258b3 fix: preserve vllm-omni imports after backend relocation (#12137) 
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>
 2026-09-19 23:39:27 +02:00
localai-org-maint-botandmudler a4b847d6b7 chore: ⬆️ Update CrispStrobe/CrispASR to 647db2c7abed1fc82a69767f6e8b3993b94b8417 (#12112) 
⬆️ Update CrispStrobe/CrispASR

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 19:48:26 +02:00
localai-org-maint-botandmudler 8b01583e70 chore: ⬆️ Update 0xShug0/audio.cpp to a074d6b8cdb16b89cd028876e83629a538d49b9a (#12125) 
⬆️ Update 0xShug0/audio.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:29:01 +02:00
localai-org-maint-botandmudler 908182d690 chore: ⬆️ Update leejet/stable-diffusion.cpp to 2ea8aff7ef603977dc2ece7856bf9736dba96652 (#12127) 
⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:28:49 +02:00
localai-org-maint-botandmudler e7d295e5f1 chore: ⬆️ Update ggml-org/llama.cpp to 50631b3d2c569ad8e5c112090cd28570b1268ee0 (#12129) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:28:28 +02:00
localai-org-maint-botandmudler 365fb57bf2 chore: ⬆️ Update ggml-org/whisper.cpp to 5670d5c0bbcb148feabef84400a07cfca9aa3b30 (#12130) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:28:16 +02:00
localai-org-maint-botandmudler 99682b768e chore: ⬆️ Update ikawrakow/ik_llama.cpp to 2ae132fa601ea06818ed3584f50f7eb4f72d4967 (#12131) 
⬆️ Update ikawrakow/ik_llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:28:06 +02:00
localai-org-maint-botandmudler 2681232d5e chore: ⬆️ Update mudler/vllm.cpp to f3cd97e379fbeca4e50415edbdd52d2517b98ef8 (#12132) 
⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:27:51 +02:00
localai-org-maint-botandmudler 215a654f21 chore: ⬆️ Update ServeurpersoCom/omnivoice.cpp to cd6922ac3cb465f1c0a22465e77db21d367204fe (#12126) 
⬆️ Update ServeurpersoCom/omnivoice.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-19 09:27:30 +02:00
dependabot[bot] eaf04c8b6b chore(deps): bump grpcio from 1.83.1 to 1.84.0 in /backend/python/rerankers (#12104) 
chore(deps): bump grpcio in /backend/python/rerankers

Bumps [grpcio](https://github.com/grpc/grpc) from 1.83.1 to 1.84.0.
- [Release notes](https://github.com/grpc/grpc/releases)
- [Commits](https://github.com/grpc/grpc/compare/v1.83.1...v1.84.0)

---
updated-dependencies:
- dependency-name: grpcio
  dependency-version: 1.84.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-09-18 22:04:06 +02:00
dependabot[bot] 727360f3da chore(deps): bump grpcio from 1.83.1 to 1.84.0 in /backend/python/common/template (#12101) 
chore(deps): bump grpcio in /backend/python/common/template

Bumps [grpcio](https://github.com/grpc/grpc) from 1.83.1 to 1.84.0.
- [Release notes](https://github.com/grpc/grpc/releases)
- [Commits](https://github.com/grpc/grpc/compare/v1.83.1...v1.84.0)

---
updated-dependencies:
- dependency-name: grpcio
  dependency-version: 1.84.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-09-18 22:03:24 +02:00
dependabot[bot] 012bc796f2 chore(deps): bump grpcio from 1.83.1 to 1.84.0 in /backend/python/vllm (#12099) 
Bumps [grpcio](https://github.com/grpc/grpc) from 1.83.1 to 1.84.0.
- [Release notes](https://github.com/grpc/grpc/releases)
- [Commits](https://github.com/grpc/grpc/compare/v1.83.1...v1.84.0)

---
updated-dependencies:
- dependency-name: grpcio
  dependency-version: 1.84.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-09-18 22:03:07 +02:00
dependabot[bot] 7821dfcd5e chore(deps): bump protobuf from 7.35.0 to 7.36.1 in /backend/python/transformers (#12098) 
chore(deps): bump protobuf in /backend/python/transformers

Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 7.35.0 to 7.36.1.
- [Release notes](https://github.com/protocolbuffers/protobuf/releases)
- [Commits](https://github.com/protocolbuffers/protobuf/commits)

---
updated-dependencies:
- dependency-name: protobuf
  dependency-version: 7.36.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-09-18 22:02:54 +02:00
localai-org-maint-botandEttore Di Giacinto 3d63736c56 feat(vllm-cpp): add video_lora_dir option for runtime prompt-activated LoRA (#12119) 
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>
 2026-09-18 10:36:36 +02:00
localai-org-maint-botandmudler e73c67f592 chore: ⬆️ Update 0xShug0/audio.cpp to f2b4937306daa25f5c78520f3c626ed31495a37a (#12086) 
⬆️ Update 0xShug0/audio.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 09:00:08 +02:00
localai-org-maint-botandmudler a5565badf1 chore: ⬆️ Update ikawrakow/ik_llama.cpp to dc31024448b8f18eac0cd5c2e200b6c7e015ef7a (#12088) 
⬆️ Update ikawrakow/ik_llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:57:43 +02:00
localai-org-maint-botandmudler c97502cbb6 chore: ⬆️ Update leejet/stable-diffusion.cpp to cc515a01f9d0e3f6b975234cc934b807f55bcd35 (#12087) 
⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:56:07 +02:00
localai-org-maint-botandmudler b8723447a3 chore: ⬆️ Update mudler/vllm.cpp to e27e6d1c8f9ccd2803d37030f8a677507fe6e314 (#12089) 
⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:55:50 +02:00
localai-org-maint-botandmudler 4ca04b0dc0 chore: ⬆️ Update PABannier/sam3.cpp to 416186c501d060df7ca02989d49b38080f5f81f3 (#12091) 
⬆️ Update PABannier/sam3.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:53:32 +02:00
localai-org-maint-botandmudler 11e0b70c3c chore: ⬆️ Update ggml-org/llama.cpp to 972d2313bc0bf0a45f634f77d95c9fb03aeab12c (#12090) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:52:34 +02:00
localai-org-maint-botandmudler a5995333e2 chore: ⬆️ Update NVIDIA/NeMo-Speech.cpp to 07003daa7eefea542076310722ccaa89709ee3c3 (#12115) 
⬆️ Update NVIDIA/NeMo-Speech.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:52:13 +02:00
localai-org-maint-botandmudler bbcf4559ce chore: ⬆️ Update ServeurpersoCom/omnivoice.cpp to c2257c833333f222d64dc9d437afdcece33ceb0b (#12116) 
⬆️ Update ServeurpersoCom/omnivoice.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-18 08:52:00 +02:00
Richard Palethorpe 2facfc0d88 feat: Add kimodo.cpp and 3D animation API/UI (#12095) 
* 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>
 2026-09-18 06:12:03 +01:00
localai-org-maint-botandmudler 7ad0cbf259 chore: ⬆️ Update CrispStrobe/CrispASR to ba3499e7c7f6013a73738cad530b252d59675f49 (#12092) 
⬆️ Update CrispStrobe/CrispASR

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-17 08:10:52 +02:00
localai-org-maint-botandmudler 1be130880c chore: ⬆️ Update antirez/ds4 to 8db1d1d155cb0400a86a86b9c62d0defb3a6148b (#12093) 
⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-17 08:10:41 +02:00
localai-org-maint-botandmudler 43e89ae552 chore: ⬆️ Update PrismML-Eng/llama.cpp to 7dffb158de30ebb8ef9d64f33c6b0b2d7c1e6313 (#12072) 
⬆️ Update PrismML-Eng/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 19:39:48 +02:00
localai-org-maint-botandmudler 456a77e155 chore: ⬆️ Update ggml-org/llama.cpp to 38a5b42d9a3e82e0a586bcd1caed121f36c87a73 (#12075) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 19:39:32 +02:00
localai-org-maint-botandEttore Di Giacinto 60679e5de6 [vllm-cpp] wire lora_adapters/lora_scales into DiT load-time fusion (#12082) 
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>
 2026-09-16 19:39:16 +02:00
localai-org-maint-botandmudler 7ac9604011 chore: ⬆️ Update mudler/vllm.cpp to b54db871e8478d0a3450132fa793d30cc336b321 (#12074) 
⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:56:35 +02:00
localai-org-maint-botandmudler 60a4e872da chore: ⬆️ Update ggml-org/whisper.cpp to da54572229bcf64ba367d96c7ef15770376c4280 (#12076) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:56:26 +02:00
localai-org-maint-botandmudler bca37c1678 chore: ⬆️ Update 0xShug0/audio.cpp to 4af143229384fb6da3f373dc87de145ae954609b (#12073) 
⬆️ Update 0xShug0/audio.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:55:32 +02:00
localai-org-maint-botandmudler 8bc2fcdf1f chore: ⬆️ Update CrispStrobe/CrispASR to 89dfbc05d1466f6c7517986c6ff85179507431f8 (#12077) 
⬆️ Update CrispStrobe/CrispASR

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:27:45 +02:00
localai-org-maint-botandmudler e7a382a7a3 chore: ⬆️ Update ikawrakow/ik_llama.cpp to d85a1d7e91e5bc2f83a796542a8d5c436d32c99f (#12078) 
⬆️ Update ikawrakow/ik_llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:27:20 +02:00
localai-org-maint-botandmudler 27cf5b917e chore: ⬆️ Update ServeurpersoCom/omnivoice.cpp to 3c30bdcfe6cc53121bd7a7b377bf8b55f526efa3 (#12079) 
⬆️ Update ServeurpersoCom/omnivoice.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-16 08:27:01 +02:00
localai-org-maint-botandEttore Di Giacinto 5a24c8a2a2 fix(qwen-tts): restore CUDA 13 SDPA fallback (#12067) 
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>
 2026-09-15 15:30:23 +02:00
localai-org-maint-botandmudler 5ce83ceb46 chore: ⬆️ Update leejet/stable-diffusion.cpp to 59c23bce0d82be3a922023ab811194f05b3e2faa (#12061) 
⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 09:34:35 +02:00
localai-org-maint-botandmudler 13087829c5 chore: ⬆️ Update ggml-org/whisper.cpp to 1d549b3cecc2d98d76d4ddc2edca0d1512f5d7a0 (#12060) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 09:34:13 +02:00
localai-org-maint-botandmudler 6d0f12702b chore: ⬆️ Update ServeurpersoCom/omnivoice.cpp to 3d341e55d365423476f8739d396b9a03d5277055 (#12059) 
⬆️ Update ServeurpersoCom/omnivoice.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 09:03:39 +02:00
localai-org-maint-botandmudler 790c53fa27 chore: ⬆️ Update ggml-org/llama.cpp to 96ffdc41ceb055e1c2d3d96667ae6d9f0ccb710b (#12057) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 09:01:50 +02:00
localai-org-maint-botandmudler 287e425c64 chore: ⬆️ Update PrismML-Eng/llama.cpp to 6ac5eb087009a762a3f61876f7dc152bc8600bf4 (#12055) 
⬆️ Update PrismML-Eng/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 09:01:39 +02:00
localai-org-maint-botandmudler d1ad8a600f chore: ⬆️ Update antirez/ds4 to 9139e2ae58a41503968a500f36f75895c1ba63fc (#12062) 
⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 01:05:54 +02:00
localai-org-maint-botandmudler 211b5983ac chore: ⬆️ Update mudler/vllm.cpp to 67c81102777296fdd506945860eb3030b9fad71a (#12053) 
⬆️ Update mudler/vllm.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 00:58:12 +02:00