feat: auto select llama-cpp cuda runtime #2306
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Sertac Ozercan <[email protected]>
Signed-off-by: Sertac Ozercan <[email protected]>
Signed-off-by: Sertac Ozercan <[email protected]>
Signed-off-by: Sertac Ozercan <[email protected]>
Signed-off-by: Sertac Ozercan <[email protected]>
Signed-off-by: Sertac Ozercan <[email protected]>
✅ Deploy Preview for localai canceled.
|
Signed-off-by: Sertac Ozercan <[email protected]>
Closed
mudler
reviewed
May 13, 2024
Makefile
Outdated
|
|
||
| backend-assets/grpc/llama-cpp-fallback: backend-assets/grpc | ||
| cp -rf backend/cpp/llama backend/cpp/llama-fallback | ||
| $(MAKE) -C backend/cpp/llama-fallback purge | ||
| $(info ${GREEN}I llama-cpp build info:fallback${RESET}) | ||
| CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server | ||
| CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server |
There was a problem hiding this comment.
Thanks for adding -DLLAMA_AVX=off, should have been here and was an oversight!
mudler
reviewed
May 13, 2024
Makefile
Outdated
| ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-fallback | ||
| ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-cuda |
There was a problem hiding this comment.
this probably would make it fail non-cuda builds - maybe we can have an ENABLE_CUDA to work with only when we run make dist?
mudler
previously approved these changes
May 13, 2024
Signed-off-by: Ettore Di Giacinto <[email protected]>
mudler
force-pushed
the
auto-select-variant-cuda
branch
from
f346d83
to
94d96c7
Compare
Signed-off-by: mudler <[email protected]>
mudler
force-pushed
the
auto-select-variant-cuda
branch
from
e2fb46b
to
d917ec8
Compare
mudler
previously approved these changes
May 13, 2024
Signed-off-by: mudler <[email protected]>
Signed-off-by: mudler <[email protected]>
There could be other reasons for which the default binary may fail. For example we might have detected an Nvidia GPU, however the user might not have the drivers/cuda libraries installed in the system, and so it would fail to start. We keep the fallback of llama.cpp at the end of the llama.cpp backends to try to fallback loading in case things go wrong Signed-off-by: mudler <[email protected]>
Signed-off-by: mudler <[email protected]>
mudler
previously approved these changes
May 13, 2024
sozercan
commented
May 14, 2024
sozercan
commented
May 14, 2024
| @@ -104,7 +109,7 @@ ENTRY: | |||
| // First has more priority | |||
| priorityList := []string{ | |||
| // First llama.cpp and llama-ggml | |||
| LLamaCPP, LlamaGGML, Gpt4All, | |||
| LLamaCPP, LlamaGGML, Gpt4All, LLamaCPPFallback, | |||
There was a problem hiding this comment.
why fallback here? LLamaCPP should fallback automatically if runtime is not avx2 or avx
There was a problem hiding this comment.
right, but what if they fail when being started? What I was trying to do here is recovering from failures outside our control, but more related to the environment where this starts e.g. missing shared libraries goes undetected until the grpc process is started.
Example:
- Environment: box with a GPU but no cuda libs installed
- LocalAI's detect that there is a GPU and we select llama-cpp-nvidia for llama-cpp
- LocalAI start the process, libs are missing, it fails
- LocalAI does not try anymore with llama-cpp backends to load the model (which we can argue if that's the correct behavior, but my point is that a lot of kittens would die if we let LocalAI fail here without a good error message. The fallback here is acting as a safety-net to make sure it works so we should then warn the user that CUDA is not loaded)
There was a problem hiding this comment.
I see, makes sense. Current GPU detection is pretty naive so that should definitely be improved by checking for the cuda libs.
Signed-off-by: Sertac Ozercan <[email protected]>
sozercan
commented
May 14, 2024
| else | ||
| $(MAKE) backend-assets/grpc/llama-cpp-cuda | ||
| endif | ||
| $(MAKE) build |
There was a problem hiding this comment.
doesn't build call grpcs target which calls make on all the GRPC_BACKENDS including the llama-cpp variants?
There was a problem hiding this comment.
correct, I've split that off initially just for STATIC=true in order to build statically the (non-cuda) llama-cpp backends.
I've added the cuda switch here and not at the top because we don't need container images or the generic build target to include a specific backend for cuda - container images are already built with the BUILD_TYPE which compiles all the llama-cpp variants against the accellerator library for the specific container images (sycl, hipblas, cuda, etc).
mudler
reviewed
May 14, 2024
mudler
reviewed
May 14, 2024
Signed-off-by: Ettore Di Giacinto <[email protected]>
mudler
approved these changes
May 14, 2024
|
looks good here - let's tackle additions directly from master. Thanks @sozercan to put this together! |
truecharts-admin
added a commit
to truecharts/charts
that referenced
this pull request
May 25, 2024
…6.0 by renovate (#22420) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0-cublas-cuda11-ffmpeg-core` -> `v2.16.0-cublas-cuda11-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0-cublas-cuda11-core` -> `v2.16.0-cublas-cuda11-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0-cublas-cuda12-ffmpeg-core` -> `v2.16.0-cublas-cuda12-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0-cublas-cuda12-core` -> `v2.16.0-cublas-cuda12-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0-ffmpeg-core` -> `v2.16.0-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.15.0` -> `v2.16.0` | --- > [!WARNING] > Some dependencies could not be looked up. Check the Dependency Dashboard for more information. --- ### Release Notes <details> <summary>mudler/LocalAI (docker.io/localai/localai)</summary> ### [`v2.16.0`](https://togithub.com/mudler/LocalAI/releases/tag/v2.16.0) [Compare Source](https://togithub.com/mudler/LocalAI/compare/v2.15.0...v2.16.0)  ##### Welcome to LocalAI's latest update! ##### 🎉🎉🎉 woot woot! So excited to share this release, a lot of new features are landing in LocalAI!!!!! 🎉🎉🎉  ##### 🌟 Introducing Distributed Llama.cpp Inferencing Now it is possible to distribute the inferencing workload across different workers with llama.cpp models ! This feature has landed with [mudler/LocalAI#2324 and is based on the upstream work of [@​rgerganov](https://togithub.com/rgerganov) in [ggerganov/llama.cpp#6829. **How it works:** a front-end server manages the requests compatible with the OpenAI API (LocalAI) and workers (llama.cpp) are used to distribute the workload. This makes possible to run larger models split across different nodes! ##### How to use it To start workers to offload the computation you can run: local-ai llamacpp-worker <listening_address> <listening_port> However, you can also follow the llama.cpp README and building the rpc-server (https://github.com/ggerganov/llama.cpp/blob/master/examples/rpc/README.md), which is still compatible with LocalAI. When starting the LocalAI server, which is going to accept the API requests, you can set a list of workers IP/address by specifying the addresses with `LLAMACPP_GRPC_SERVERS`: ```bash LLAMACPP_GRPC_SERVERS="address1:port,address2:port" local-ai run ``` At this point the workload hitting in the LocalAI server should be distributed across the nodes! ##### 🤖 Peer2Peer llama.cpp LocalAI is the **first** AI Free, Open source project offering complete, decentralized, peer2peer while private, LLM inferencing on top of the libp2p protocol. There is no "public swarm" to offload the computation, but rather empowers you to build your own cluster of local and remote machines to distribute LLM computation.  This feature leverages the ability of llama.cpp to distribute the workload explained just above and features from one of my other projects, https://github.com/mudler/edgevpn. LocalAI builds on top of the twos, and allows to create a private peer2peer network between nodes, without the need of centralizing connections or manually configuring IP addresses: it unlocks totally decentralized, private, peer-to-peer inferencing capabilities. Works also behind different NAT-ted networks (uses DHT and mDNS as discovery mechanism). **How it works:** A pre-shared token can be generated and shared between workers and the server to form a private, decentralized, p2p network. You can see the feature in action here:  ##### How to use it 1. Start the server with `--p2p`: ```bash ./local-ai run --p2p ##### 1:02AM INF loading environment variables from file envFile=.env ##### 1:02AM INF Setting logging to info ##### 1:02AM INF P2P mode enabled ##### 1:02AM INF No token provided, generating one ##### 1:02AM INF Generated Token: ##### XXXXXXXXXXX ##### 1:02AM INF Press a button to proceed ``` A token is displayed, copy it and press enter. You can re-use the same token later restarting the server with `--p2ptoken` (or `P2P_TOKEN`). 2. Start the workers. Now you can copy the local-ai binary in other hosts, and run as many workers with that token: ```bash TOKEN=XXX ./local-ai p2p-llama-cpp-rpc ##### 1:06AM INF loading environment variables from file envFile=.env ##### 1:06AM INF Setting logging to info ##### {"level":"INFO","time":"2024-05-19T01:06:01.794+0200","caller":"config/config.go:288","message":"connmanager disabled\n"} ##### {"level":"INFO","time":"2024-05-19T01:06:01.794+0200","caller":"config/config.go:295","message":" go-libp2p resource manager protection enabled"} ##### {"level":"INFO","time":"2024-05-19T01:06:01.794+0200","caller":"config/config.go:409","message":"max connections: 100\n"} ##### 1:06AM INF Starting llama-cpp-rpc-server on '127.0.0.1:34371' ##### {"level":"INFO","time":"2024-05-19T01:06:01.794+0200","caller":"node/node.go:118","message":" Starting EdgeVPN network"} ##### create_backend: using CPU backend ##### Starting RPC server on 127.0.0.1:34371, backend memory: 31913 MB ##### 2024/05/19 01:06:01 failed to sufficiently increase receive buffer size (was: 208 kiB, wanted: 2048 kiB, got: 416 kiB). # See https://github.com/quic-go/quic-go/wiki/UDP-Buffer-Sizes for details. ##### {"level":"INFO","time":"2024-05-19T01:06:01.805+0200","caller":"node/node.go:172","message":" Node ID: 12D3KooWJ7WQAbCWKfJgjw2oMMGGss9diw3Sov5hVWi8t4DMgx92"} ##### {"level":"INFO","time":"2024-05-19T01:06:01.806+0200","caller":"node/node.go:173","message":" Node Addresses: [/ip4/127.0.0.1/tcp/44931 /ip4/127.0.0.1/udp/33251/quic-v1/webtransport/certhash/uEiAWAhZ-W9yx2ZHnKQm3BE_ft5jjoc468z5-Rgr9XdfjeQ/certhash/uEiB8Uwn0M2TQBELaV2m4lqypIAY2S-2ZMf7lt_N5LS6ojw /ip4/127.0.0.1/udp/35660/quic-v1 /ip4/192.168.68.110/tcp/44931 /ip4/192.168.68.110/udp/33251/quic-v1/webtransport/certhash/uEiAWAhZ-W9yx2ZHnKQm3BE_ft5jjoc468z5-Rgr9XdfjeQ/certhash/uEiB8Uwn0M2TQBELaV2m4lqypIAY2S-2ZMf7lt_N5LS6ojw /ip4/192.168.68.110/udp/35660/quic-v1 /ip6/::1/tcp/41289 /ip6/::1/udp/33160/quic-v1/webtransport/certhash/uEiAWAhZ-W9yx2ZHnKQm3BE_ft5jjoc468z5-Rgr9XdfjeQ/certhash/uEiB8Uwn0M2TQBELaV2m4lqypIAY2S-2ZMf7lt_N5LS6ojw /ip6/::1/udp/35701/quic-v1]"} ##### {"level":"INFO","time":"2024-05-19T01:06:01.806+0200","caller":"discovery/dht.go:104","message":" Bootstrapping DHT"} ``` (Note you can also supply the token via args) At this point, you should see in the server logs messages stating that new workers are found 3. Now you can start doing inference as usual on the server (the node used on step 1) Interested in to try it out? As we are still updating the documentation, you can read the full instructions here [mudler/LocalAI#2343 ##### 📜 Advanced Function calling support with Mixed JSON Grammars LocalAI gets better at function calling with mixed grammars! With this release, LocalAI introduces a transformative capability: support for mixed JSON BNF grammars. It allows to specify a grammar for the LLM that allows to output structured JSON and free text. **How to use it:** To enable mixed grammars, you can set in the `YAML` configuration file `function.mixed_mode = true`, for example: ```yaml function: ##### disable injecting the "answer" tool disable_no_action: true grammar: ##### This allows the grammar to also return messages mixed_mode: true ``` This feature significantly enhances LocalAI's ability to interpret and manipulate JSON data coming from the LLM through a more flexible and powerful grammar system. Users can now combine multiple grammar types within a single JSON structure, allowing for dynamic parsing and validation scenarios. Grammars can also turned off entirely and leave the user to determine how the data is parsed from the LLM to be correctly interpretated by LocalAI to be still compliant to the OpenAI REST spec. For example, to interpret Hermes results, one can just annotate regexes in `function.json_regex_match` to extract the LLM response: ```yaml function: grammar: disable: true ##### disable injecting the "answer" tool disable_no_action: true return_name_in_function_response: true json_regex_match: - "(?s)<tool_call>(.*?)</tool_call>" - "(?s)<tool_call>(.*?)" replace_llm_results: ##### Drop the scratchpad content from responses - key: "(?s)<scratchpad>.*</scratchpad>" value: "" replace_function_results: ##### Replace everything that is not JSON array or object, just in case. - key: '(?s)^[^{\[]*' value: "" - key: '(?s)[^}\]]*$' value: "" ##### Drop the scratchpad content from responses - key: "(?s)<scratchpad>.*</scratchpad>" value: "" ``` Note that regex can still be used when enabling mixed grammars is enabled. This is especially important for models which does not support grammars - such as transformers or OpenVINO models, that now can support as well function calling. As we update the docs, further documentation can be found in the PRs that you can find in the changelog below. ##### 🚀 New Model Additions and Updates  Our model gallery continues to grow with exciting new additions like Aya-35b, Mistral-0.3, Hermes-Theta and updates to existing models ensuring they remain at the cutting edge. This release is having major enhancements on tool calling support. Besides working on making our default models in AIO images more performant - now you can try an enhanced out-of-the-box experience with function calling in the Hermes model family ( [Hermes-2-Pro-Mistral](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF) and [Hermes-2-Theta-Llama-3](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF)) ##### Our LocalAI function model!  I have fine-tuned a function call model specific to leverage entirely the grammar support of LocalAI, you can find it in the model gallery already and on [huggingface](https://huggingface.co/mudler/LocalAI-Llama3-8b-Function-Call-v0.2) ##### 🔄 Single Binary Release: Simplified Deployment and Management In our continuous effort to streamline the user experience and deployment process, LocalAI v2.16.0 proudly introduces a single binary release. This enhancement, thanks to [@​sozercan](https://togithub.com/sozercan)'s contributions, consolidates all variants (CUDA and non-cuda releases) and dependencies into one compact executable file. This change simplifies the installation and update processes, reduces compatibility issues, and speeds up the setup for new users and existing deployments as now binary releases are even more portable than ever! ##### 🔧 Bug Fixes and Improvements A host of bug fixes have been implemented to ensure smoother operation and integration. Key fixes include enhancements to the Intel build process, stability adjustments for setuptools in Python backends, and critical updates ensuring the successful build of p2p configurations. ##### Migrating Python Backends: From Conda to UV LocalAI has migrated its Python backends from Conda to UV. This transition, thanks to [@​cryptk](https://togithub.com/cryptk) contributions, enhances the efficiency and scalability of our backend operations. Users will experience faster setup times and reduced complexity, streamlining the development process and making it easier to manage dependencies across different environments. ##### 📣 Let's Make Some Noise! A gigantic THANK YOU to everyone who’s contributed—your feedback, bug squashing, and feature suggestions are what make LocalAI shine. To all our heroes out there supporting other users and sharing their expertise, you’re the real MVPs! Remember, LocalAI thrives on community support—not big corporate bucks. If you love what we're building, show some love! A shoutout on social (@​LocalAI_OSS and @​mudler_it on twitter/X), joining our sponsors, or simply starring us on GitHub makes all the difference. Also, if you haven't yet joined our Discord, come on over! Here's the link: https://discord.gg/uJAeKSAGDy Thanks a ton, and.. enjoy this release! ##### What's Changed ##### Bug fixes 🐛 - build: do not specify a BUILD_ID by default by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2284 - fix: add missing openvino/optimum/etc libraries for Intel, fixes [#​2289](https://togithub.com/mudler/LocalAI/issues/2289) by [@​cryptk](https://togithub.com/cryptk) in [mudler/LocalAI#2292 - add setuptools for openvino by [@​fakezeta](https://togithub.com/fakezeta) in [mudler/LocalAI#2301 - fix: add setuptools to all requirements-intel.txt files for python backends by [@​cryptk](https://togithub.com/cryptk) in [mudler/LocalAI#2333 - ci: correctly build p2p in GO_TAGS by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2369 - ci: generate specific image for intel builds by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2374 - fix: stablediffusion binary by [@​sozercan](https://togithub.com/sozercan) in [mudler/LocalAI#2385 ##### Exciting New Features 🎉 - feat: migrate python backends from conda to uv by [@​cryptk](https://togithub.com/cryptk) in [mudler/LocalAI#2215 - feat: create bash library to handle install/run/test of python backends by [@​cryptk](https://togithub.com/cryptk) in [mudler/LocalAI#2286 - feat(grammar): support models with specific construct by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2291 - feat(ui): display number of available models for installation by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2298 - feat: auto select llama-cpp cpu variant by [@​sozercan](https://togithub.com/sozercan) in [mudler/LocalAI#2305 - feat(llama.cpp): add `flash_attention` and `no_kv_offloading` by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2310 - feat(functions): support models with no grammar and no regex by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2315 - feat(functions): allow to set JSON matcher by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2319 - feat: auto select llama-cpp cuda runtime by [@​sozercan](https://togithub.com/sozercan) in [mudler/LocalAI#2306 - feat(llama.cpp): add distributed llama.cpp inferencing by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2324 - feat(functions): mixed JSON BNF grammars by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2328 - feat(functions): simplify parsing, read functions as list by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2340 - feat(functions): Enable true regex replacement for the regexReplacement option by [@​lenaxia](https://togithub.com/lenaxia) in [mudler/LocalAI#2341 - feat(backends): add openvoice backend by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2334 - feat(webui): statically embed js/css assets by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2348 - feat(functions): allow to use JSONRegexMatch unconditionally by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2349 - feat(functions): don't use yaml.MapSlice by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2354 - build: add sha by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2356 - feat(llama.cpp): Totally decentralized, private, distributed, p2p inference by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2343 - feat(functions): relax mixedgrammars by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2365 - models(gallery): add mistral-0.3 and command-r, update functions by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2388 ##### 🧠 Models - models(gallery): add aloe by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2283 - models(gallery): add Llama-3-8B-Instruct-abliterated by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2288 - models(gallery): add l3-chaoticsoliloquy-v1.5-4x8b by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2295 - models(gallery): add jsl-medllama-3-8b-v2.0 by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2296 - models(gallery): add llama-3-refueled by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2297 - models(gallery): add aura-llama-Abliterated by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2309 - models(gallery): add Bunny-llama by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2311 - models(gallery): add lumimaidv2 by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2312 - models(gallery): add orthocopter by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2313 - fix(gallery) Correct llama3-8b-instruct model file by [@​tannisroot](https://togithub.com/tannisroot) in [mudler/LocalAI#2330 - models(gallery): add hermes-2-theta-llama-3-8b by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2331 - models(gallery): add yi 6/9b, sqlcoder, sfr-iterative-dpo by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2335 - models(gallery): add anita by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2344 - models(gallery): add master-yi by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2345 - models(gallery): update poppy porpoise mmproj by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2346 - models(gallery): add LocalAI-Llama3-8b-Function-Call-v0.2-GGUF by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2355 - models(gallery): add stheno by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2358 - fix(gallery): checksum Meta-Llama-3-70B-Instruct.Q4\_K_M.gguf - [#​2364](https://togithub.com/mudler/LocalAI/issues/2364) by [@​Nold360](https://togithub.com/Nold360) in [mudler/LocalAI#2366 - models(gallery): add phi-3-medium-4k-instruct by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2367 - models(gallery): add hercules and helpingAI by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2376 - ci(checksum_checker): do get sha from hf API when available by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2380 - models(gallery): ⬆️ update checksum by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2383 - models(gallery): ⬆️ update checksum by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2386 - models(gallery): add aya-35b by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2391 ##### 📖 Documentation and examples - docs: Update semantic-todo/README.md by [@​eltociear](https://togithub.com/eltociear) in [mudler/LocalAI#2294 - Add Home Assistant Integration by [@​valentinfrlch](https://togithub.com/valentinfrlch) in [mudler/LocalAI#2387 - Add warning for running the binary on MacOS by [@​mauromorales](https://togithub.com/mauromorales) in [mudler/LocalAI#2389 ##### 👒 Dependencies - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2281 - ⬆️ Update docs version mudler/LocalAI by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2280 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2285 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2290 - feat(swagger): update swagger by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2302 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2303 - ⬆️ Update ggerganov/whisper.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2317 - ⬆️ Update ggerganov/whisper.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2326 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2316 - ⬆️ Update ggerganov/whisper.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2329 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2337 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2339 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2342 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2351 - ⬆️ Update ggerganov/whisper.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2352 - dependencies(grpcio): bump to fix CI issues by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2362 - deps(llama.cpp): update and adapt API changes by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#2381 - ⬆️ Update ggerganov/whisper.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2361 - ⬆️ Update go-skynet/go-bert.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1225 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#2360 ##### Other Changes - refactor: Minor improvements to BackendConfigLoader by [@​dave-gray101](https://togithub.com/dave-gray101) in [mudler/LocalAI#2353 ##### New Contributors - [@​tannisroot](https://togithub.com/tannisroot) made their first contribution in [mudler/LocalAI#2330 - [@​lenaxia](https://togithub.com/lenaxia) made their first contribution in [mudler/LocalAI#2341 - [@​valentinfrlch](https://togithub.com/valentinfrlch) made their first contribution in [mudler/LocalAI#2387 **Full Changelog**: mudler/LocalAI@v2.15.0...v2.16.0 </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://togithub.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4zNzcuNCIsInVwZGF0ZWRJblZlciI6IjM3LjM3Ny40IiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIiwibGFiZWxzIjpbImF1dG9tZXJnZSIsInVwZGF0ZS9kb2NrZXIvZ2VuZXJhbC9ub24tbWFqb3IiXX0=-->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Merge after #2305
Notes for Reviewers
Signed commits