Commit Graph

  • eed5706994 refactor: backend/service split, channel-based llm flow (#1963) Dave 2024-04-13 03:45:34 -04:00
  • 1981154f49 fix: dont commit generated files to git (#1993) cryptk 2024-04-13 02:37:32 -05:00
  • a8ebf6f575 fix: respect concurrency from parent build parameters when building GRPC (#2023) cryptk 2024-04-13 02:14:32 -05:00
  • 912d2dccfa ⬆️ Update ggerganov/llama.cpp (#2024) LocalAI [bot] 2024-04-13 09:13:00 +02:00
  • fcb63aed8a build(deps): bump follow-redirects from 1.15.2 to 1.15.6 in /examples/langchain/langchainjs-localai-example (#2020) dependabot[bot] 2024-04-12 15:36:46 +00:00
  • 0e549424e7 Update dependabot_auto.yml Ettore Di Giacinto 2024-04-12 15:59:25 +02:00
  • 69d638268b Update dependabot_auto.yml Ettore Di Giacinto 2024-04-12 15:57:13 +02:00
  • 18eea9088a Update dependabot_auto.yml Ettore Di Giacinto 2024-04-12 15:38:34 +02:00
  • fb105837ba Update secscan.yaml Ettore Di Giacinto 2024-04-12 15:37:56 +02:00
  • 7e52c8e21a Update CONTRIBUTING.md Ettore Di Giacinto 2024-04-12 15:27:40 +02:00
  • d068839896 ⬆️ Update docs version mudler/LocalAI (#2013) LocalAI [bot] 2024-04-12 08:40:19 +02:00
  • e0dee52a2a build(deps): bump the pip group across 4 directories with 8 updates (#2017) dependabot[bot] 2024-04-12 00:53:43 -04:00
  • 677e20756b ⬆️ Update ggerganov/llama.cpp (#2014) LocalAI [bot] 2024-04-12 00:49:41 +02:00
  • b2785ff06e feat(gallery): support ConfigURLs (#2012) Ettore Di Giacinto 2024-04-12 00:49:23 +02:00
  • da82ce81b5 build(deps): bump github.com/opencontainers/runc from 1.1.5 to 1.1.12 (#2000) dependabot[bot] 2024-04-11 18:57:33 +00:00
  • 70c4f110a4 Update overview.md Ettore Di Giacinto 2024-04-11 20:18:05 +02:00
  • 099bd54ff2 ci: try to build on macos14 (#2011) Ettore Di Giacinto 2024-04-11 19:22:30 +02:00
  • 12c0d9443e feat: use tokenizer.apply_chat_template() in vLLM (#1990) Ludovic Leroux 2024-04-11 13:20:22 -04:00
  • cbda06fb96 build(deps): bump github.com/gofiber/fiber/v2 from 2.52.0 to 2.52.4 (#2008) dependabot[bot] 2024-04-11 16:52:54 +00:00
  • b1a242251c ci: fixup upload artifact name Ettore Di Giacinto 2024-04-11 18:26:03 +02:00
  • fce606fc0f build(deps): bump github.com/charmbracelet/glamour from 0.6.0 to 0.7.0 (#2004) dependabot[bot] 2024-04-11 15:41:58 +00:00
  • b606c7b768 build(deps): bump actions/upload-artifact from 3 to 4 (#2007) dependabot[bot] 2024-04-11 14:44:02 +00:00
  • 0a6956b029 build(deps): bump actions/cache from 3 to 4 (#2006) dependabot[bot] 2024-04-11 14:35:27 +00:00
  • 821cf0e3fd build(deps): bump peter-evans/create-pull-request from 5 to 6 (#2005) dependabot[bot] 2024-04-11 13:58:04 +00:00
  • 11a0418510 build(deps): bump actions/setup-go from 4 to 5 (#2003) dependabot[bot] 2024-04-11 13:10:32 +00:00
  • 40781ac013 build(deps): bump actions/checkout from 3 to 4 (#2002) dependabot[bot] 2024-04-11 12:48:30 +00:00
  • fdfd868953 build(deps): bump github.com/gofiber/fiber/v2 from 2.52.0 to 2.52.1 (#2001) dependabot[bot] 2024-04-11 12:21:52 +00:00
  • 0795975486 build(deps): bump github.com/docker/docker from 20.10.7+incompatible to 24.0.9+incompatible (#1999) dependabot[bot] 2024-04-11 11:44:34 +00:00
  • a49248d29f build(deps): bump google.golang.org/protobuf from 1.31.0 to 1.33.0 (#1998) dependabot[bot] 2024-04-11 11:07:45 +00:00
  • 0004ec8be3 fix(autogptq): do not use_triton with qwen-vl (#1985) v2.12.4 release/v2.12.4 Sebastian.W 2024-04-10 18:36:10 +08:00
  • 182fef339d Create dependabot_auto.yml Ettore Di Giacinto 2024-04-11 12:13:06 +02:00
  • c74dec7e38 Add dependabot.yml Ettore Di Giacinto 2024-04-11 11:47:54 +02:00
  • b4548ad72d feat: add flash-attn in nvidia and rocm envs (#1995) Ludovic Leroux 2024-04-11 03:44:39 -04:00
  • e152b07b74 ⬆️ Update ggerganov/llama.cpp (#1991) LocalAI [bot] 2024-04-11 09:22:07 +02:00
  • 0e44a4e664 ⬆️ Update docs version mudler/LocalAI (#1988) LocalAI [bot] 2024-04-11 09:19:46 +02:00
  • 24d7dadfed feat: kong cli refactor fixes #1955 (#1974) cryptk 2024-04-11 02:19:24 -05:00
  • 92005b9c02 Update openai-functions.md Ettore Di Giacinto 2024-04-10 16:30:57 +02:00
  • 636d487dc8 Update gpt-vision.md Ettore Di Giacinto 2024-04-10 16:30:03 +02:00
  • 93f51d80d4 Update gpt-vision.md Ettore Di Giacinto 2024-04-10 16:29:46 +02:00
  • 36da11a0ee deps: Update version of vLLM to add support of Cohere Command_R model in vLLM inference (#1975) Koen Farell 2024-04-10 14:25:26 +03:00
  • d23e73b118 fix(autogptq): do not use_triton with qwen-vl (#1985) Sebastian.W 2024-04-10 18:36:10 +08:00
  • d692b2c32a ci: push latest images for dockerhub (#1984) v2.12.3 Ettore Di Giacinto 2024-04-10 10:31:59 +02:00
  • 7e2f8bb408 ⬆️ Update ggerganov/whisper.cpp (#1980) LocalAI [bot] 2024-04-10 09:08:00 +02:00
  • 951e39d36c ⬆️ Update ggerganov/llama.cpp (#1979) LocalAI [bot] 2024-04-10 09:07:41 +02:00
  • aeb3f835ae ⬆️ Update docs version mudler/LocalAI (#1978) LocalAI [bot] 2024-04-10 09:07:21 +02:00
  • cc3d601836 ci: fixup latest image push v2.12.1 Ettore Di Giacinto 2024-04-09 09:49:11 +02:00
  • 2bbb221fb1 tests(petals): temp disable v2.12.0 Ettore Di Giacinto 2024-04-08 21:28:59 +00:00
  • 195be10050 ⬆️ Update ggerganov/llama.cpp (#1973) LocalAI [bot] 2024-04-08 23:26:52 +02:00
  • a38618db02 fix regression #1971 (#1972) fakezeta 2024-04-08 22:33:51 +02:00
  • efcca15d3f ⬆️ Update ggerganov/llama.cpp (#1970) LocalAI [bot] 2024-04-08 08:38:47 +02:00
  • a153b628c2 ⬆️ Update ggerganov/whisper.cpp (#1969) LocalAI [bot] 2024-04-08 08:38:17 +02:00
  • f36d86ba6d fix(hermes-2-pro-mistral): correct dashes in template to suppress newlines (#1966) Ettore Di Giacinto 2024-04-07 18:23:47 +02:00
  • 74492a81c7 doc(quickstart): fix typo Ettore Di Giacinto 2024-04-07 11:06:35 +02:00
  • ed13782986 ⬆️ Update ggerganov/llama.cpp (#1964) LocalAI [bot] 2024-04-07 10:32:10 +02:00
  • 8342553214 fix(llama.cpp): set better defaults for llama.cpp (#1961) Ettore Di Giacinto 2024-04-06 22:56:45 +02:00
  • 8aa5f5a660 ⬆️ Update ggerganov/llama.cpp (#1960) LocalAI [bot] 2024-04-06 21:15:25 +02:00
  • b2d9e3f704 ⬆️ Update ggerganov/llama.cpp (#1959) LocalAI [bot] 2024-04-05 08:41:55 +02:00
  • f744e1f931 ⬆️ Update ggerganov/whisper.cpp (#1958) LocalAI [bot] 2024-04-05 08:41:35 +02:00
  • b85dad0286 feat: first pass at improving logging (#1956) cryptk 2024-04-04 02:24:22 -05:00
  • 3851b51d98 ⬆️ Update ggerganov/llama.cpp (#1953) LocalAI [bot] 2024-04-04 00:27:57 +02:00
  • ff77d3bc22 fix(seed): generate random seed per-request if -1 is set (#1952) Ettore Di Giacinto 2024-04-03 22:25:47 +02:00
  • 93cfec3c32 ci: correctly tag latest and aio images Ettore Di Giacinto 2024-04-03 11:30:12 +02:00
  • 89560ef87f fix(ci): manually tag latest images (#1948) Ettore Di Giacinto 2024-04-02 19:25:46 +02:00
  • 9bc209ba73 fix(welcome): stable model list (#1949) Ettore Di Giacinto 2024-04-02 19:25:32 +02:00
  • 84e0dc3246 fix(hermes-2-pro-mistral): correct stopwords (#1947) Ettore Di Giacinto 2024-04-02 15:38:00 +02:00
  • 4d4d76114d ⬆️ Update ggerganov/llama.cpp (#1941) LocalAI [bot] 2024-04-02 09:16:04 +02:00
  • 86bc5f1350 fix: use exec in entrypoint scripts to fix signal handling (#1943) cryptk 2024-04-02 02:15:44 -05:00
  • e8f02c083f fix(functions): respect when selected from string (#1940) Ettore Di Giacinto 2024-04-01 19:39:54 +02:00
  • ebb1fcedea fix(hermes-2-pro-mistral): add stopword for toolcall (#1939) Ettore Di Giacinto 2024-04-01 11:48:35 +02:00
  • 66f90f8dc1 ⬆️ Update ggerganov/llama.cpp (#1937) LocalAI [bot] 2024-04-01 08:59:23 +02:00
  • 3c778b538a Update phi-2-orange.yaml Ettore Di Giacinto 2024-03-31 13:06:41 +02:00
  • 35290e146b fix(grammar): respect JSONmode and grammar from user input (#1935) Ettore Di Giacinto 2024-03-31 13:04:09 +02:00
  • 784657a652 ⬆️ Update ggerganov/llama.cpp (#1934) LocalAI [bot] 2024-03-31 00:27:38 +01:00
  • 831efa8893 ⬆️ Update ggerganov/whisper.cpp (#1933) LocalAI [bot] 2024-03-31 00:27:16 +01:00
  • 957f428fd5 fix(tools): correctly render tools response in templates (#1932) Ettore Di Giacinto 2024-03-30 19:02:07 +01:00
  • 61e5e6bc36 fix(swagger): do not specify a host (#1930) Ettore Di Giacinto 2024-03-30 12:04:41 +01:00
  • eab4a91a9b fix(aio): correctly detect intel systems (#1931) Ettore Di Giacinto 2024-03-30 12:04:32 +01:00
  • 2bba62ca4d ⬆️ Update ggerganov/llama.cpp (#1928) LocalAI [bot] 2024-03-29 23:52:01 +01:00
  • bcdc83b46d Update quickstart.md Ettore Di Giacinto 2024-03-29 23:00:06 +01:00
  • 92fbdfd06f feat(swagger): update (#1929) Ettore Di Giacinto 2024-03-29 22:48:58 +01:00
  • 93702e39d4 feat(build): adjust number of parallel make jobs (#1915) cryptk 2024-03-29 16:32:40 -05:00
  • a7fc89c207 ⬆️ Update ggerganov/whisper.cpp (#1927) LocalAI [bot] 2024-03-29 22:29:50 +01:00
  • 123a5a2e16 feat(swagger): Add swagger API doc (#1926) Ettore Di Giacinto 2024-03-29 22:29:33 +01:00
  • ab2f403dd0 ⬆️ Update ggerganov/whisper.cpp (#1924) LocalAI [bot] 2024-03-29 00:13:59 +01:00
  • b9c5e14e2c ⬆️ Update ggerganov/llama.cpp (#1923) LocalAI [bot] 2024-03-29 00:13:38 +01:00
  • bf65ed6eb8 feat(webui): add partials, show backends associated to models (#1922) Ettore Di Giacinto 2024-03-28 21:52:52 +01:00
  • 4e79294f97 Update README.md Ettore Di Giacinto 2024-03-28 19:52:40 +01:00
  • 8477e8fac3 Update quickstart.md Ettore Di Giacinto 2024-03-28 18:28:30 +01:00
  • 13ccd2afef docs(aio-usage): update docs to show examples (#1921) Ettore Di Giacinto 2024-03-28 18:16:58 +01:00
  • 23b833d171 Update run-other-models.md Ettore Di Giacinto 2024-03-28 12:42:37 +01:00
  • 07c49ee4b8 ⬆️ Update ggerganov/whisper.cpp (#1914) LocalAI [bot] 2024-03-27 23:53:13 +01:00
  • 07c4bdda7c ⬆️ Update ggerganov/llama.cpp (#1913) LocalAI [bot] 2024-03-27 22:57:59 +01:00
  • 2266d8263c Update README.md Ettore Di Giacinto 2024-03-27 22:48:46 +01:00
  • 160eb48b2b Update quickstart.md Ettore Di Giacinto 2024-03-27 22:47:59 +01:00
  • 0c0efc871c fix(build): better CI logging and correct some build failure modes in Makefile (#1899) cryptk 2024-03-27 15:12:19 -05:00
  • 7ef5f3b473 ⬆️ Update M0Rf30/go-tiny-dream (#1911) Gianluca Boiano 2024-03-27 21:12:04 +01:00
  • 66ee4afb95 feat(welcome): add simple welcome page (#1912) Ettore Di Giacinto 2024-03-27 21:10:58 +01:00
  • 93f0b7ae03 update hot topics Ettore Di Giacinto 2024-03-27 18:17:12 +01:00
  • 8210ffcb6c feat: Token Stream support for Transformer, fix: missing package for OpenVINO (#1908) fakezeta 2024-03-27 17:50:35 +01:00
  • e7cbe32601 feat: Openvino runtime for transformer backend and streaming support for Openvino and CUDA (#1892) fakezeta 2024-03-27 00:31:43 +01:00