LocalAI v2.21.0stable Released Sep 24, 2024
โš ๏ธ Breaking Change Impact Score: 7/10

LocalAI v2.21.0 โ€” Release Notes & Engineering Impact

Source available โ€” automated, not human-reviewed

Component: localai ยท Channel: stable. Automated analysis, not a compatibility certification. How this works.

Analysis updated: 2026-11-01.

Breaking-change evidence from the source

  • Breaking Changes ๐Ÿ›  * chore(exllama): drop exllama backend by @mudler in https://github.com/mudler/LocalAI/pull/3536 * chore(aio): rename gpt-4-vision-preview to gpt-4o by @mudler in https://github.com/mudler/LocalAI/pull/3597
Read the original context โ†—
Source flags breaking changes โ€” review applicability
๐Ÿ“„ .MD
โšก Executive Summary (TL;DR)

LocalAI v2.21.0. Source highlight: LocalAI v2.21 release is out!

Who Does This Impact? (Role-Based Analysis)

๐Ÿ’ป Software Engineers & Devs

Check the source notes against the package and APIs you use before upgrading.

๐Ÿ“Š Product & Engineering Leads

Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.

โš™๏ธ DevOps & Security

Verify the target version, runtime requirements and rollback procedure in the official documentation.

โš ๏ธ Breaking Changes & Deprecations (1)

  • Breaking Changes ๐Ÿ›  * chore(exllama): drop exllama backend by @mudler in https://github.com/mudler/LocalAI/pull/3536 * chore(aio): rename gpt-4-vision-preview to gpt-4o by @mudler in https://github.com/mudler/LocalAI/pull/3597

โœจ New Features & Capabilities (6)

  • feat: elevenlabs `sound-generation` api
  • feat(vllm): add support for embeddings
  • feat: add endpoint to list system informations
  • feat: extract output with regexes from LLMs
  • feat: allow setting trust_remote_code for sentencetransformers backend
  • feat(api): allow to pass videos to backends

๐Ÿ”ง Bug Fixes & Patches (6)

  • fix(p2p): correctly allow to pass extra args to llama.cpp
  • fix(model-loading): keep track of open GRPC Clients
  • fix(tts): check error before inspecting result
  • fix(shutdown): do not shutdown immediately busy backends
  • fix(parler-tts): fix install with sycl
  • fix(ci): fixup checksum scanning pipeline
๐Ÿ“„ View Raw Release Notes (Original Developer Log)
<!-- Release notes generated using configuration in .github/release.yml at master --> ## :bulb: Highlights! LocalAI v2.21 release is out! - Deprecation of the `exllama` backend - AIO images now have `gpt-4o` instead of `gpt-4-vision-preview` for Vision API - vLLM backend now supports embeddings - New endpoint to list system information (`/system`) - `trust_remote_code` is now respected by `sentencetransformers` - Auto warm-up and load models on start - `coqui` backend switched to the community-maintained fork ## What's Changed ### Breaking Changes ๐Ÿ›  * chore(exllama): drop exllama backend by @mudler in https://github.com/mudler/LocalAI/pull/3536 * chore(aio): rename gpt-4-vision-preview to gpt-4o by @mudler in https://github.com/mudler/LocalAI/pull/3597 ### Exciting New Features ๐ŸŽ‰ * feat: elevenlabs `sound-generation` api by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3355 * feat(vllm): add support for embeddings by @mudler in https://github.com/mudler/LocalAI/pull/3440 * feat: add endpoint to list system informations by @mudler in https://github.com/mudler/LocalAI/pull/3449 * feat: extract output with regexes from LLMs by @mudler in https://github.com/mudler/LocalAI/pull/3491 * feat: allow setting trust_remote_code for sentencetransformers backend by @Nyralei in https://github.com/mudler/LocalAI/pull/3552 * feat(api): allow to pass videos to backends by @mudler in https://github.com/mudler/LocalAI/pull/3601 * feat(api): allow to pass audios to backends by @mudler in https://github.com/mudler/LocalAI/pull/3603 * feat: auto load into memory on startup by @sozercan in https://github.com/mudler/LocalAI/pull/3627 * feat(coqui): switch to maintained community fork by @mudler in https://github.com/mudler/LocalAI/pull/3625 ### Bug fixes :bug: * fix(p2p): correctly allow to pass extra args to llama.cpp by @mudler in https://github.com/mudler/LocalAI/pull/3368 * fix(model-loading): keep track of open GRPC Clients by @mudler in https://github.com/mudler/LocalAI/pull/3377 * fix(tts): check error before inspecting result by @mudler in https://github.com/mudler/LocalAI/pull/3415 * fix(shutdown): do not shutdown immediately busy backends by @mudler in https://github.com/mudler/LocalAI/pull/3543 * fix(parler-tts): fix install with sycl by @mudler in https://github.com/mudler/LocalAI/pull/3624 * fix(ci): fixup checksum scanning pipeline by @mudler in https://github.com/mudler/LocalAI/pull/3631 * fix(hipblas): do not push all variants to hipblas builds by @mudler in https://github.com/mudler/LocalAI/pull/3630 ### ๐Ÿง  Models * chore(model-gallery): add more quants for popular models by @mudler in https://github.com/mudler/LocalAI/pull/3365 * models(gallery): add phi-3.5 by @mudler in https://github.com/mudler/LocalAI/pull/3376 * models(gallery): add calme-2.1-phi3.5-4b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/3383 * models(gallery): add magnum-v3-34b by @mudler in https://github.com/mudler/LocalAI/pull/3384 * models(gallery): add phi-3.5-vision by @mudler in https://github.com/mudler/LocalAI/pull/3421 * Revert "models(gallery): add phi-3.5-vision" by @mudler in https://github.com/mudler/LocalAI/pull/3422 * chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/3425 * feat: Added Piper voice it-paola-medium by @fakezeta in https://github.com/mudler/LocalAI/pull/3434 * chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/3442 * models(gallery): add hubble-4b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/3444 * chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/3446 * models(gallery): add yi-coder (and variants) by @mudler in https://github.com/mudler/LocalAI/pull/3482 * chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/3486 * models(gallery): add reflection-llama-3.1-70b by @mudler in https://github.com/mudler/LocalAI/pull/3487 * models(gallery): add athena-codegemma-2-2b-it by @mudler in https://github.com/mudler/LocalAI/pull/3490 * models(gallery): add azure_dusk-v0.2-iq-imatrix by @mudler in https://github.com/mudler/LocalAI/pull/3538 * models(gallery): add mn-12b-lyra-v4-iq-imatrix by @mudler in https://github.com/mudler/LocalAI/pull/3539 * models(gallery): add datagemma models by @mudler in https://github.com/mudler/LocalAI/pull/3540 * models(gallery): add l3.1-8b-niitama-v1.1-iq-imatrix by @mudler in https://github.com/mudler/LocalAI/pull/3550 * models(gallery): add llama-3.1-8b-stheno-v3.4-iq-imatrix by @mudler in https://github.com/mudler/LocalAI/pull/3551 * fix: `gallery/index.yaml` comment spacing by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3585 * models(gallery): add qwen2.5-14b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/3607 * models(gallery): add qwen2.5-math-7b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/3609 * models(gallery): add qwen2.5-14b_uncencored by @mudler in https://github.com/mudler/LocalAI/pull/3610 * models(gallery): add qwen2.5-coder-7b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/3611 * models(gallery): add qwen2.5-math-72b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/3612 * models(gallery): add qwen2.5-0.5b-instruct, qwen2.5-1.5b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/3613 * models(gallery): add qwen2.5 32B, 72B, 32B Instruct by @mudler in https://github.com/mudler/LocalAI/pull/3614 * models(gallery): add llama-3.1-supernova-lite-reflection-v1.0-i1 by @mudler in https://github.com/mudler/LocalAI/pull/3615 * models(gallery): add llama-3.1-supernova-lite by @mudler in https://github.com/mudler/LocalAI/pull/3616 * models(gallery): add llama3.1-8b-shiningvaliant2 by @mudler in https://github.com/mudler/LocalAI/pull/3617 * models(gallery): add buddy2 by @mudler in https://github.com/mudler/LocalAI/pull/3618 * models(gallery): add llama-3.1-8b-arliai-rpmax-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/3619 * Fix NeuralDaredevil URL by @nyx4ris in https://github.com/mudler/LocalAI/pull/3621 * models(gallery): add nightygurps-14b-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/3633 * models(gallery): add gemma-2-9b-arliai-rpmax-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/3634 * models(gallery): add gemma-2-2b-arliai-rpmax-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/3635 * models(gallery): add acolyte-22b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/3636 ### ๐Ÿ“– Documentation and examples * docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/3366 * chore(docs): add Vulkan images links by @mudler in https://github.com/mudler/LocalAI/pull/3620 ### ๐Ÿ‘’ Dependencies * chore: :arrow_up: Update ggerganov/llama.cpp to `3ba780e2a8f0ffe13f571b27f0bbf2ca5a199efc` by @localai-bot in https://github.com/mudler/LocalAI/pull/3361 * chore(deps): Bump openai from 1.41.1 to 1.42.0 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3390 * chore(deps): Bump docs/themes/hugo-theme-relearn from `82a5e98` to `3a0ae52` by @dependabot in https://github.com/mudler/LocalAI/pull/3391 * chore(deps): Bump idna from 3.7 to 3.8 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3399 * chore(deps): Bump llama-index from 0.10.65 to 0.11.1 in /examples/chainlit by @dependabot in https://github.com/mudler/LocalAI/pull/3404 * chore(deps): Bump llama-index from 0.10.67.post1 to 0.11.1 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3406 * chore(deps): Bump marshmallow from 3.21.3 to 3.22.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3400 * chore(deps): Bump openai from 1.40.5 to 1.42.0 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3405 * chore(deps): Bump openai from 1.41.1 to 1.42.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3401 * chore(deps): update edgevpn to v0.28 by @mudler in https://github.com/mudler/LocalAI/pull/3412 * chore(deps): Bump langchain from 0.2.14 to 0.2.15 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3453 * chore(deps): Bump certifi from 2024.7.4 to 2024.8.30 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3457 * chore(deps): Bump yarl from 1.9.4 to 1.9.7 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3459 * chore(deps): Bump langchain-community from 0.2.12 to 0.2.15 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3461 * chore(deps): Bump llama-index from 0.11.1 to 0.11.4 in /examples/chainlit by @dependabot in https://github.com/mudler/LocalAI/pull/3462 * chore(deps): Bump llama-index from 0.11.1 to 0.11.4 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3467 * chore(deps): Bump docs/themes/hugo-theme-relearn from `3a0ae52` to `550a6ee` by @dependabot in https://github.com/mudler/LocalAI/pull/3472 * chore(deps): Bump openai from 1.42.0 to 1.43.0 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3452 * chore(deps): Bump langchain from 0.2.14 to 0.2.15 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3460 * chore(deps): Bump openai from 1.42.0 to 1.43.0 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3468 * chore(deps): Bump langchain from 0.2.14 to 0.2.15 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3466 * chore(deps): Bump streamlit from 1.37.1 to 1.38.0 in /examples/streamlit-bot by @dependabot in https://github.com/mudler/LocalAI/pull/3465 * chore(deps): Bump openai from 1.42.0 to 1.43.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3456 * chore(deps): Bump langchain-community from 0.2.15 to 0.2.16 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3500 * chore(deps): Bump openai from 1.43.0 to 1.44.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3504 * chore(deps): Bump docs/themes/hugo-theme-relearn from `550a6ee` to `f696f60` by @dependabot in https://github.com/mudler/LocalAI/pull/3505 * chore(deps): Bump langchain from 0.2.15 to 0.2.16 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3507 * chore(deps): Bump peter-evans/create-pull-request from 6 to 7 by @dependabot in https://github.com/mudler/LocalAI/pull/3518 * chore(deps): Bump openai from 1.43.0 to 1.44.0 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3522 * chore(deps): Bump langchain from 0.2.15 to 0.2.16 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3502 * chore(deps): Bump numpy from 2.1.0 to 2.1.1 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3503 * chore(deps): Bump llama-index from 0.11.4 to 0.11.7 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3508 * chore(deps): Bump langchain from 0.2.15 to 0.2.16 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3521 * chore(deps): Bump openai from 1.43.0 to 1.44.1 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3532 * chore(deps): Bump yarl from 1.9.7 to 1.11.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3501 * chore(deps): Bump llama-index from 0.11.4 to 0.11.7 in /examples/chainlit by @dependabot in https://github.com/mudler/LocalAI/pull/3516 * chore(deps): update llama.cpp to 6262d13e0b2da91f230129a93a996609a2fa2f2 by @mudler in https://github.com/mudler/LocalAI/pull/3549 * chore(deps): Bump docs/themes/hugo-theme-relearn from `f696f60` to `d5a0ee0` by @dependabot in https://github.com/mudler/LocalAI/pull/3558 * chore(deps): Bump setuptools from 72.1.0 to 75.1.0 in /backend/python/coqui by @dependabot in https://github.com/mudler/LocalAI/pull/3554 * chore(deps): Bump langchain from 0.2.16 to 0.3.0 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3559 * chore(deps): Bump openai from 1.44.1 to 1.45.1 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3556 * chore(deps): Bump setuptools from 72.1.0 to 75.1.0 in /backend/python/autogptq by @dependabot in https://github.com/mudler/LocalAI/pull/3553 * chore(deps): Bump securego/gosec from 2.21.0 to 2.21.2 by @dependabot in https://github.com/mudler/LocalAI/pull/3561 * chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python/transformers-musicgen by @dependabot in https://github.com/mudler/LocalAI/pull/3564 * chore(deps): Bump setuptools from 72.1.0 to 75.1.0 in /backend/python/parler-tts by @dependabot in https://github.com/mudler/LocalAI/pull/3565 * chore(deps): Bump sentence-transformers from 3.0.1 to 3.1.0 in /backend/python/sentencetransformers by @dependabot in https://github.com/mudler/LocalAI/pull/3566 * chore(deps): Bump llama-index from 0.11.7 to 0.11.9 in /examples/chainlit by @dependabot in https://github.com/mudler/LocalAI/pull/3567 * chore(deps): Bump weaviate-client from 4.6.7 to 4.8.1 in /examples/chainlit by @dependabot in https://github.com/mudler/LocalAI/pull/3568 * chore(deps): Bump setuptools from 72.1.0 to 75.1.0 in /backend/python/vall-e-x by @dependabot in https://github.com/mudler/LocalAI/pull/3570 * chore(deps): Bump greenlet from 3.0.3 to 3.1.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3571 * chore(deps): Bump setuptools from 70.3.0 to 75.1.0 in /backend/python/diffusers by @dependabot in https://github.com/mudler/LocalAI/pull/3575 * chore(deps): Bump setuptools from 70.3.0 to 75.1.0 in /backend/python/bark by @dependabot in https://github.com/mudler/LocalAI/pull/3574 * chore(deps): Bump setuptools from 72.1.0 to 75.1.0 in /backend/python/rerankers by @dependabot in https://github.com/mudler/LocalAI/pull/3578 * chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python/transformers by @dependabot in https://github.com/mudler/LocalAI/pull/3579 * chore(deps): Bump setuptools from 70.3.0 to 75.1.0 in /backend/python/vllm by @dependabot in https://github.com/mudler/LocalAI/pull/3580 * chore(deps): Bump langchain from 0.2.16 to 0.3.0 in /examples/langchain-chroma by @dependabot in https://github.com/mudler/LocalAI/pull/3557 * chore(deps): Bump openai from 1.44.0 to 1.45.1 in /examples/functions by @dependabot in https://github.com/mudler/LocalAI/pull/3560 * chore(deps): Bump langchain from 0.2.16 to 0.3.0 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3577 * chore(deps): Bump openai from 1.44.0 to 1.45.1 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3573 * chore(deps): Bump pypinyin from 0.50.0 to 0.53.0 in /backend/python/openvoice by @dependabot in https://github.com/mudler/LocalAI/pull/3562 * chore(deps): Bump yarl from 1.11.0 to 1.11.1 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3643 * chore(deps): Bump urllib3 from 2.2.2 to 2.2.3 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3646 * chore(deps): Bump idna from 3.8 to 3.10 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3644 * chore(deps): Bump sqlalchemy from 2.0.32 to 2.0.35 in /examples/langchain/langchainpy-localai-example by @dependabot in https://github.com/mudler/LocalAI/pull/3649 ### Other Changes * feat: external backend launching log improvements and relative path support by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3348 * Update quickstart.md by @grant-wilson in https://github.com/mudler/LocalAI/pull/3373 * feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/3370 * fix: devcontainer `utils.sh` ssh copy improvements by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3372 * chore(cuda): reduce binary size by @mudler in https://github.com/mudler/LocalAI/pull/3379 * chore(deps): update edgevpn by @mudler in https://github.com/mudler/LocalAI/pull/3385 * chore: :arrow_up: Update ggerganov/llama.cpp to `7d787ed96c32be18603c158ab0276992cf0dc346` by @localai-bot in https://github.com/mudler/LocalAI/pull/3409 * chore: :arrow_up: Update ggerganov/llama.cpp to `20f1789dfb4e535d64ba2f523c64929e7891f428` by @localai-bot in https://github.com/mudler/LocalAI/pull/3417 * chore: :arrow_up: Update ggerganov/llama.cpp to `9fe94ccac92693d4ae1bc283ff0574e8b3f4e765` by @localai-bot in https://github.com/mudler/LocalAI/pull/3424 * chore(cli): be consistent between workers and expose ExtraLLamaCPPArgs to both by @mudler in https://github.com/mudler/LocalAI/pull/3428 * chore(tests): replace runaway models for tests by @mudler in https://github.com/mudler/LocalAI/pull/3432 * chore(model-loader): increase test coverage of model loader by @mudler in https://github.com/mudler/LocalAI/pull/3433 * chore(deps): update llama.cpp by @mudler in https://github.com/mudler/LocalAI/pull/3438 * chore: :arrow_up: Update ggerganov/llama.cpp to `a47667cff41f5a198eb791974e0afcc1cddd3229` by @localai-bot in https://github.com/mudler/LocalAI/pull/3441 * chore: :arrow_up: Update ggerganov/llama.cpp to `8f1d81a0b6f50b9bad72db0b6fcd299ad9ecd48c` by @localai-bot in https://github.com/mudler/LocalAI/pull/3445 * fix: untangle pkg/grpc and core/schema for Transcription by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3419 * chore(deps): update whisper.cpp by @mudler in https://github.com/mudler/LocalAI/pull/3443 * chore: :arrow_up: Update ggerganov/llama.cpp to `48baa61eccdca9205daf8d620ba28055c2347b64` by @localai-bot in https://github.com/mudler/LocalAI/pull/3474 * chore: :arrow_up: Update ggerganov/whisper.cpp to `5236f0278420ab776d1787c4330678d80219b4b6` by @localai-bot in https://github.com/mudler/LocalAI/pull/3475 * chore: :arrow_up: Update ggerganov/llama.cpp to `8962422b1c6f9b8b15f5aeaea42600bcc2d44177` by @localai-bot in https://github.com/mudler/LocalAI/pull/3478 * fix: purge a few remaining runway model references by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3480 * chore: :arrow_up: Update ggerganov/llama.cpp to `581c305186a0ff93f360346c57e21fe16e967bb7` by @localai-bot in https://github.com/mudler/LocalAI/pull/3481 * chore: :arrow_up: Update ggerganov/llama.cpp to `4db04784f96757d74f74c8c110c2a00d55e33514` by @localai-bot in https://github.com/mudler/LocalAI/pull/3485 * feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/3484 * chore: :arrow_up: Update ggerganov/llama.cpp to `815b1fb20a53e439882171757825bacb1350de04` by @localai-bot in https://github.com/mudler/LocalAI/pull/3489 * chore: :arrow_up: Update ggerganov/whisper.cpp to `5caa19240d55bfd6ee316d50fbad32c6e9c39528` by @localai-bot in https://github.com/mudler/LocalAI/pull/3494 * fix: speedup and improve cachability of docker build of `builder-sd` by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3430 * chore: :arrow_up: Update ggerganov/whisper.cpp to `a551933542d956ae84634937acd2942eb40efaaf` by @localai-bot in https://github.com/mudler/LocalAI/pull/3534 * chore(deps): update llama.cpp by @mudler in https://github.com/mudler/LocalAI/pull/3497 * chore(gosec): fix CI by @mudler in https://github.com/mudler/LocalAI/pull/3537 * chore: :arrow_up: Update ggerganov/llama.cpp to `feff4aa8461da7c432d144c11da4802e41fef3cf` by @localai-bot in https://github.com/mudler/LocalAI/pull/3542 * chore: :arrow_up: Update ggerganov/whisper.cpp to `049b3a0e53c8a8e4c4576c06a1a4fccf0063a73f` by @localai-bot in https://github.com/mudler/LocalAI/pull/3548 * feat: auth v2 - supersedes #2894 by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3476 * chore: :arrow_up: Update ggerganov/llama.cpp to `23e0d70bacaaca1429d365a44aa9e7434f17823b` by @localai-bot in https://github.com/mudler/LocalAI/pull/3581 * Revert "chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python/transformers" by @mudler in https://github.com/mudler/LocalAI/pull/3586 * chore(refactor): drop duplicated shutdown logics by @mudler in https://github.com/mudler/LocalAI/pull/3589 * Revert "chore(deps): Bump securego/gosec from 2.21.0 to 2.21.2" by @mudler in https://github.com/mudler/LocalAI/pull/3590 * chore: :arrow_up: Update ggerganov/llama.cpp to `8b836ae731bbb2c5640bc47df5b0a78ffcb129cb` by @localai-bot in https://github.com/mudler/LocalAI/pull/3591 * chore: :arrow_up: Update ggerganov/whisper.cpp to `5b1ce40fa882e9cb8630b48032067a1ed2f1534f` by @localai-bot in https://github.com/mudler/LocalAI/pull/3592 * chore: :arrow_up: Update ggerganov/llama.cpp to `64c6af3195c3cd4aa3328a1282d29cd2635c34c9` by @localai-bot in https://github.com/mudler/LocalAI/pull/3598 * feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/3604 * chore: :arrow_up: Update ggerganov/llama.cpp to `6026da52d6942b253df835070619775d849d0258` by @localai-bot in https://github.com/mudler/LocalAI/pull/3605 * chore: :arrow_up: Update ggerganov/whisper.cpp to `34972dbe221709323714fc8402f2e24041d48213` by @localai-bot in https://github.com/mudler/LocalAI/pull/3623 * chore: :arrow_up: Update ggerganov/llama.cpp to `63351143b2ea5efe9f8b9c61f553af8a51f1deff` by @localai-bot in https://github.com/mudler/LocalAI/pull/3622 * chore: :arrow_up: Update ggerganov/llama.cpp to `d09770cae71b416c032ec143dda530f7413c4038` by @localai-bot in https://github.com/mudler/LocalAI/pull/3626 * chore: :arrow_up: Update ggerganov/llama.cpp to `c35e586ea57221844442c65a1172498c54971cb0` by @localai-bot in https://github.com/mudler/LocalAI/pull/3629 * chore: :arrow_up: Update ggerganov/llama.cpp to `f0c7b5edf82aa200656fd88c11ae3a805d7130bf` by @localai-bot in https://github.com/mudler/LocalAI/pull/3653 * test: preliminary tests and merge fix for authv2 by @dave-gray101 in https://github.com/mudler/LocalAI/pull/3584 ## New Contributors * @grant-wilson made their first contribution in https://github.com/mudler/LocalAI/pull/3373 * @Nyralei made their first contribution in https://github.com/mudler/LocalAI/pull/3552 * @nyx4ris made their first contribution in https://github.com/mudler/LocalAI/pull/3621 **Full Changelog**: https://github.com/mudler/LocalAI/compare/v2.20.1...v2.21.0