141 Commits

Author	SHA1	Message	Date
Ettore Di Giacinto	61cc76c455	chore(autogptq): drop archived backend (#5214) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-04-19 15:52:29 +02:00
Dave	134fe2705c	fix: ensure git-lfs is present (#5078) ... devcontainer clean builds had issue with git-lfs -- should this be installed for _all_ images for safety? Signed-off-by: Dave Lee <dave@gray101.com>	2025-03-27 22:23:28 +01:00
Ettore Di Giacinto	0a748b009e	chore(ci): avoit cache hits until the ci gRPC job is fixed ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-02-12 09:11:40 +01:00
Ettore Di Giacinto	8fd3ace9a1	chore(grpcio): bump to 1.70 (#4798) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-02-10 18:38:53 +01:00
Ettore Di Giacinto	5177837ab0	chore: detect and enable avx512 builds (#4675) ... chore(avx512): add support Fixes https://github.com/mudler/LocalAI/issues/4662 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-24 08:26:44 +01:00
Ettore Di Giacinto	073eaec729	chore(openvoice): drop backend (#4673) ... The project (MeloTTS) has been quite since long, newer backends are much performant and better quality overall. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-23 10:00:36 +01:00
Ettore Di Giacinto	318225f631	chore(parler-tts): drop backend (#4672) ... We support at this point more extensive backends that are SOTA and support also voice cloning, and many other features. This backend is superseded and also poses significant maintenance burden as there is an open issue https://github.com/mudler/LocalAI/issues/3941 which is still open as it deps are pinning old versions of grpc. Closes https://github.com/mudler/LocalAI/issues/3941 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-23 09:46:16 +01:00
Ettore Di Giacinto	89429a439b	feat(transformers): add support to Mamba (#4669) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-23 09:30:47 +01:00
Ettore Di Giacinto	e426ab7c23	feat(faster-whisper): add backend (#4666) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-23 08:06:18 +01:00
Ettore Di Giacinto	e15d29aba2	chore(stablediffusion-ncn): drop in favor of ggml implementation (#4652) ... * chore(stablediffusion-ncn): drop in favor of ggml implementation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): drop stablediffusion build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): add Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): try to fixup current tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tests improvements Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): use quality to specify step Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): switch to sd-1.5 also increase prep time for downloading models Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-22 19:34:16 +01:00
Ettore Di Giacinto	1e9bf19c8d	feat(transformers): merge sentencetransformers backend (#4624) ... * merge sentencetransformers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add alias to silently redirect sentencetransformers to transformers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add alias also for transformers-musicgen Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop from makefile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move tests from sentencetransformers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Remove sentencetransformers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Remove tests from CI (part of transformers) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Do not always try to load the tokenizer Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix typo Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tiny adjustments Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-18 18:30:30 +01:00
Ettore Di Giacinto	8027fdf1c7	feat(transformers): merge musicgen functionalities to a single backend (#4620) ... * feat(transformers): merge musicgen functionalities to a single backend So we optimize space Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * specify type in tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Some adaptations for the MusicgenForConditionalGeneration type Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-17 17:01:16 +01:00
Ettore Di Giacinto	7d0ac1ea3f	chore(vall-e-x): Drop backend (#4619) ... There are many new architectures that are SOTA and replaces vall-e-x nowadays. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-17 09:35:10 +01:00
Ettore Di Giacinto	acb2eb23c8	feat(tts): Add Kokoro backend (#4616) ... * feat(kokoro): Add new TTS backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add kokoro to images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Support combined voices Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Ignore pt and onnx Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add plbert and istfnet Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-16 22:23:09 +01:00
Ettore Di Giacinto	478014ca18	feat(Dockerfile): allow to skip driver installation (#4447) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-12-22 21:28:38 +01:00
Ettore Di Giacinto	d454118887	fix(container-images): install uv as system package (#4094) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-11-08 11:47:43 +01:00
Ettore Di Giacinto	e06daf437a	chore(Dockerfile): default to cmake from package manager (#3746) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-10-07 16:42:56 +02:00
Ettore Di Giacinto	fbca9f82fd	fix(vllm): bump cmake - vllm requires it (#3744) ... * fix(vllm): bump cmake - vllm requires it Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): try to increase coqui timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-10-07 11:22:55 +02:00
Dave	90cacb9692	test: preliminary tests and merge fix for authv2 (#3584) ... * add api key to existing app tests, add preliminary auth test Signed-off-by: Dave Lee <dave@gray101.com> * small fix, run test Signed-off-by: Dave Lee <dave@gray101.com> * status on non-opaque Signed-off-by: Dave Lee <dave@gray101.com> * tweak auth error Signed-off-by: Dave Lee <dave@gray101.com> * exp Signed-off-by: Dave Lee <dave@gray101.com> * quick fix on real laptop Signed-off-by: Dave Lee <dave@gray101.com> * add downloader version that allows providing an auth header Signed-off-by: Dave Lee <dave@gray101.com> * stash some devcontainer fixes during testing Signed-off-by: Dave Lee <dave@gray101.com> * s2 Signed-off-by: Dave Lee <dave@gray101.com> * s Signed-off-by: Dave Lee <dave@gray101.com> * done with experiment Signed-off-by: Dave Lee <dave@gray101.com> * done with experiment Signed-off-by: Dave Lee <dave@gray101.com> * after merge fix Signed-off-by: Dave Lee <dave@gray101.com> * rename and fix Signed-off-by: Dave Lee <dave@gray101.com> --------- Signed-off-by: Dave Lee <dave@gray101.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-09-24 09:32:48 +02:00
Ettore Di Giacinto	51cba89682	fix(hipblas): do not push all variants to hipblas builds (#3630) ... Like with CUDA builds, we don't need all the variants when we are compiling against the accelerated variants - in this way we save space and we avoid to exceed embedFS golang size limits. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-09-23 11:49:07 +02:00
Ettore Di Giacinto	25e7661de2	chore(exllama): drop exllama backend (#3536) ... * chore(exllama): drop exllama backend For polishing and cleaning up it makes now sense to drop exllama which is completely unmaintained, and was only supporting the llamav1 architecture (nowadays it's superseded by llamav1) . Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(gosec): fix CI downgrade to latest known version of the gosec action Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-09-13 19:52:13 +00:00
Dave	300f2779e4	fix: speedup and improve cachability of docker build of builder-sd (#3430) ... fix: speedup and improve cachability of docker build of `builder-sd` (#3430) --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-09-10 08:57:16 +02:00
Ettore Di Giacinto	5d892f86ea	chore(cuda): reduce binary size (#3379) ... fix(cuda): reduce binary size Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-26 14:47:36 +02:00
Ettore Di Giacinto	736df11454	fix(ci): pin to llvmlite 0.43 (#3342) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-20 20:14:35 +02:00
Ettore Di Giacinto	aca2c4196a	ci(Dockerfile): try to install lvm-10 from Ubuntu repositories ... Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-08-20 19:36:11 +02:00
Ettore Di Giacinto	6aba6223c7	ci(Dockerfile): adjust deps from typos ... Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-08-20 19:21:47 +02:00
Ettore Di Giacinto	d02a0f6f01	ci: add llvm dependencies ... Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-08-20 18:27:10 +02:00
Ettore Di Giacinto	b06046fe4c	chore: install llvm 10 ... Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-08-20 18:06:55 +02:00
Dave	9a8a249932	feat: devcontainer part 3 (#3318) ... * stash initial fixes, attempt to open branch inside container Signed-off-by: Dave Lee <dave@gray101.com> * add yq, from inside DC Signed-off-by: Dave Lee <dave@gray101.com> * stash progress, rebuild container Signed-off-by: Dave Lee <dave@gray101.com> * snap Signed-off-by: Dave Lee <dave@gray101.com> * split builder into builder-sd, will speed up devcontainer build times and potentially help caching in other situations. Signed-off-by: Dave Lee <dave@gray101.com> * fix yq Signed-off-by: Dave Lee <dave@gray101.com> * fix paths Signed-off-by: Dave Lee <dave@gray101.com> * fix paths - new folder to bypass the .dockerignore which _should_ exclude the other files Signed-off-by: Dave Lee <dave@gray101.com> * fix Signed-off-by: Dave Lee <dave@gray101.com> * fix ] Signed-off-by: Dave Lee <dave@gray101.com> --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-08-20 12:16:21 +02:00
Ettore Di Giacinto	dfa183551e	fix: add llvm to extra images (#3321) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-20 12:14:47 +02:00
Ettore Di Giacinto	9475a6fa05	chore: drop petals (#3316) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-20 10:01:38 +02:00
Dave	57f7900210	feat: Initial Version of vscode DevContainer (#3217) ... initial version of devcontainer --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-08-14 09:06:41 +02:00
Ettore Di Giacinto	a9757fb057	fix(cuda): downgrade to 12.0 to increase compatibility range (#2994) ... * fix(cuda): downgrade to 12.0 to increase compatibility range Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * improve messaging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-07-23 23:35:31 +02:00
Ettore Di Giacinto	bcd9e153ba	ci(Makefile): reduce binary size by compressing (#2947) ... Makefile: try to reduce binary size Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-07-22 15:39:57 +02:00
cryptk	38b3115a15	fix: cleanup indentation and remove duplicate dockerfile stanza (#2889) ... Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>	2024-07-16 01:51:15 +00:00
Rene Leonhardt	fc87507012	chore(deps): Update Dependencies (#2538) ... * chore(deps): Update dependencies Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> * chore(deps): Upgrade github.com/imdario/mergo to dario.cat/mergo Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> * remove version identifiers for MeloTTS Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> --------- Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> Signed-off-by: Dave <dave@gray101.com> Co-authored-by: Dave <dave@gray101.com>	2024-07-12 19:54:08 +00:00
Dave	fd0bc21c3e	fix abseil test issue [attempt 3] (#2769) ... * use a sed hack to jam a missing line in place for grpc's abseil version. Signed-off-by: Dave Lee <dave@gray101.com> --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-07-11 01:40:54 +00:00
Ettore Di Giacinto	2845baecd5	fix(cuda): downgrade default version from 12.5 to 12.4 (#2707) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-07-09 23:13:29 +02:00
Ettore Di Giacinto	e591ff2e74	fix(initializer): do select backends that exist (#2694) ... we were not checking if the binary exists before picking these up from the asset dir. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-07-01 22:50:36 +02:00
Ettore Di Giacinto	e84b31935c	feat(vulkan): add vulkan support to the llama.cpp backend (#2648) ... feat(vulkan): add vulkan support to llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-06-24 20:04:58 +02:00
Rene Leonhardt	43f0688a95	feat: Upgrade to CUDA 12.5 (#2601) ... Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>	2024-06-19 17:50:49 +02:00
Rene Leonhardt	b4d4c0a18f	chore(deps): Update Dockerfile (#2532) ... Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>	2024-06-10 08:40:02 +00:00
Ettore Di Giacinto	4c9623f50d	deps(whisper): update, add libcufft-dev (#2501) ... * arrow_up: Update ggerganov/whisper.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * fix(build): add libcufft-dev 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>	2024-06-06 08:41:04 +02:00
Ettore Di Giacinto	c603b95ac7	ci: pin build-time protoc (#2461) ... ci: pin protoc Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-06-01 18:59:15 +02:00
Ettore Di Giacinto	2bbc52fcc8	feat(build): add arm64 core containers (#2421) ... ci: add arm64 container images Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-28 10:34:59 +02:00
Ettore Di Giacinto	9f5c274321	feat(images): do not install python deps in the core image (#2425) ... do not install python deps in the core image Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-27 22:07:48 +02:00
Sertaç Özercan	3200a6655e	fix: gpu fetch device info (#2403) ... * fix: gpu fetch device info Signed-off-by: Sertac Ozercan <sozercan@gmail.com> * use pciutils package Signed-off-by: Sertac Ozercan <sozercan@gmail.com> --------- Signed-off-by: Sertac Ozercan <sozercan@gmail.com>	2024-05-26 09:56:06 +02:00
Ettore Di Giacinto	371d0cc1f7	ci: generate specific image for intel builds (#2374) ... ci: fix intel images until are fixed upstream Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-22 23:35:39 +02:00
Ettore Di Giacinto	f91e4e5c03	ci: correctly build p2p in GO_TAGS (#2369) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-22 10:15:36 +02:00
Ettore Di Giacinto	fdb45153fe	feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) ... * feat(llama.cpp): Enable decentralized, distributed inference As https://github.com/mudler/LocalAI/pull/2324 introduced distributed inferencing thanks to @rgerganov implementation in https://github.com/ggerganov/llama.cpp/pull/6829 in upstream llama.cpp, now it is possible to distribute the workload to remote llama.cpp gRPC server. This changeset now uses mudler/edgevpn to establish a secure, distributed network between the nodes using a shared token. The token is generated automatically when starting the server with the `--p2p` flag, and can be used by starting the workers with `local-ai worker p2p-llama-cpp-rpc` by passing the token via environment variable (TOKEN) or with args (--token). As per how mudler/edgevpn works, a network is established between the server and the workers with dht and mdns discovery protocols, the llama.cpp rpc server is automatically started and exposed to the underlying p2p network so the API server can connect on. When the HTTP server is started, it will discover the workers in the network and automatically create the port-forwards to the service locally. Then llama.cpp is configured to use the services. This feature is behind the "p2p" GO_FLAGS Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * go mod tidy Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * better message Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-20 19:17:59 +02:00