Commit Graph

  • 565648f3f7
    relay CUDA errors to the client (#825) Bruce MacDonald 2023-10-18 15:36:56 -04:00
  • 90c49bed57 moved removal of leading space into Predict Arne Müller 2023-10-18 20:08:26 +02:00
  • 3a2477174f
    Merge pull request #822 from ggozad/fix-tags-api Michael Yang 2023-10-18 09:34:00 -07:00
  • 8c6c2cbc8c When the .ollama folder is broken or there are no models return an empty list on /api/tags Yiorgis Gozadinos 2023-10-17 19:02:43 +02:00
  • 5dc0cff459 fix whitespace removal Arne Müller 2023-10-18 08:15:27 +02:00
  • c5c8b4b16a added python rag news summary Matt Williams 2023-10-17 16:41:28 -07:00
  • 8299bf76ed model: native gotemplate adapter template Michael Yang 2023-10-17 15:28:38 -07:00
  • ee4979e510 show: no template system if empty Michael Yang 2023-10-17 15:25:43 -07:00
  • 08b0e04f40
    Merge pull request #813 from jmorganca/mxyng/llama Michael Yang 2023-10-17 14:05:58 -07:00
  • b36b0b71f8 use cut prefix Michael Yang 2023-10-16 16:31:56 -07:00
  • 094df37563 remove unused struct Michael Yang 2023-10-16 16:31:29 -07:00
  • f3648fd206
    Update llama.cpp gguf to latest (#710) Bruce MacDonald 2023-10-17 16:55:16 -04:00
  • bd93a94abd
    fix MB VRAM log output (#824) Bruce MacDonald 2023-10-17 15:35:16 -04:00
  • f55bdb6f10
    Merge pull request #799 from deichbewohner/jsonmarshaling Michael Yang 2023-10-17 08:46:02 -07:00
  • 2870a9bfc8
    Merge pull request #812 from jmorganca/mxyng/fix-format-string Michael Yang 2023-10-17 08:40:49 -07:00
  • c031c211d1
    Merge pull request #809 from jmorganca/mxyng/fix-gpu Michael Yang 2023-10-17 08:40:40 -07:00
  • 68391b0055
    Add OllamaSharp for .NET (#811) Andreas Wäscher 2023-10-17 17:31:48 +02:00
  • b7e137323a
    Fix a typo (#818) Alexander F. Rødseth 2023-10-17 15:00:15 +02:00
  • 8fa3f366ad Removed newline trimming and used buffer directly in POST request. Arne Müller 2023-10-17 08:17:35 +02:00
  • fddb303f23 fix: format string wrong type Michael Yang 2023-10-16 16:14:12 -07:00
  • ad5ee20c7b
    Merge pull request #794 from ggozad/add_oterm Michael Yang 2023-10-16 15:51:55 -07:00
  • 785b4eb5bf
    Merge branch 'main' into add_oterm Michael Yang 2023-10-16 15:51:44 -07:00
  • 16ede1b30b
    Merge pull request #801 from s-kostyaev/add-ellama-community-integration Michael Yang 2023-10-16 15:51:25 -07:00
  • 17d6bbbb2a
    Merge pull request #810 from vieux/patch-1 Michael Yang 2023-10-16 15:50:57 -07:00
  • 6481b7f34c
    Update install.sh, avoid ARCH: unbound variable Victor Vieux 2023-10-16 14:40:24 -07:00
  • cb4a80b693 fix: regression unsupported metal types Michael Yang 2023-10-16 14:37:17 -07:00
  • 68d7255bd3
    show request to server rather than local check (#778) Bruce MacDonald 2023-10-16 17:27:25 -04:00
  • 9ef2fce33a
    Merge pull request #768 from jmorganca/mxyng/bytes Michael Yang 2023-10-16 12:42:41 -07:00
  • 43eaba3d60
    Merge pull request #787 from jmorganca/mxyng/server-version2 Michael Yang 2023-10-16 09:59:30 -07:00
  • 1af493c5a0 server: print version on start Michael Yang 2023-10-13 16:08:35 -07:00
  • a0c3e989de
    deprecate modelfile embed command (#759) Bruce MacDonald 2023-10-16 11:07:37 -04:00
  • 7af0fdce48 add ellama community integration Sergey Kostyaev 2023-10-16 16:39:10 +07:00
  • ee94693b1a handling unescaped json marshaling Arne Müller 2023-10-16 11:15:55 +02:00
  • 731dbdc1a5 Add oterm to community integrations Yiorgis Gozadinos 2023-10-15 23:20:41 +02:00
  • 4522109b11 addressing new comments after merge mattw/howtoquant Matt Williams 2023-10-15 14:17:23 -07:00
  • 06bcfbd629 cleanup docker section in readme Jeffrey Morgan 2023-10-15 02:33:25 -04:00
  • 7d7c2510f8 add docker exec command to readme Jeffrey Morgan 2023-10-15 02:31:15 -04:00
  • f9b2f999ac update readme with docker setup and link to import.md Jeffrey Morgan 2023-10-15 02:23:03 -04:00
  • c416087339 import.md: formatting and spelling Jeffrey Morgan 2023-10-15 01:39:46 -04:00
  • 6002cebd2c import.md: convert and quantize docs Jeffrey Morgan 2023-10-15 00:11:51 -04:00
  • 212bdc541c import.md: model architectures spelling Jeffrey Morgan 2023-10-15 00:07:58 -04:00
  • dca6686273 add steps for creating a Modelfile and more example commands to import.md Jeffrey Morgan 2023-10-15 00:05:47 -04:00
  • 598621afab add push script for docker images Jeffrey Morgan 2023-10-14 14:24:34 -04:00
  • 6479f49c09
    Merge pull request #773 from jmorganca/mattw/howtoquant Matt Williams 2023-10-14 08:29:39 -07:00
  • b2974a7095 applied mikes comments Matt Williams 2023-10-14 08:29:24 -07:00
  • 832b4db9d4 Use correct url for auto updates v0.1.3 Jeffrey Morgan 2023-10-13 19:04:42 -04:00
  • c43873f33b
    check update response (#785) Bruce MacDonald 2023-10-13 18:05:46 -04:00
  • 11d82d7b9b update checkvram Michael Yang 2023-10-13 14:45:50 -07:00
  • 36fe2deebf only check system memory on macos Michael Yang 2023-10-13 14:41:51 -07:00
  • 4a8931f634 check total (system + video) memory Michael Yang 2023-10-12 10:36:23 -07:00
  • bd6e38fb1a refactor memory check Michael Yang 2023-10-12 09:47:17 -07:00
  • 92189a5855 fix memory check Michael Yang 2023-10-12 09:34:16 -07:00
  • d790bf9916
    Merge pull request #783 from jmorganca/mxyng/fix-gpu-offloading Michael Yang 2023-10-13 14:36:44 -07:00
  • 35afac099a do not use gpu binary when num_gpu == 0 Michael Yang 2023-10-13 13:00:44 -07:00
  • 811c3d1900 no gpu if vram < 2GB Michael Yang 2023-10-13 12:58:54 -07:00
  • 3553d10769
    check for newer updates (#784) Bruce MacDonald 2023-10-13 17:29:46 -04:00
  • 6fe178134d
    improve api error handling (#781) Bruce MacDonald 2023-10-13 16:57:10 -04:00
  • d890890f66 use lower glibc versions in Dockerfile.build v0.1.2 Jeffrey Morgan 2023-10-13 01:06:19 -04:00
  • 89ba19feca use Go 1.21.3 in Dockerfile Jeffrey Morgan 2023-10-12 23:23:12 -04:00
  • 6f58c77671 update Dockerfile.build for linux binary builds Jeffrey Morgan 2023-10-12 22:14:20 -04:00
  • 3c975f898f update doc to refer to docker image Matt Williams 2023-10-12 15:57:50 -07:00
  • 9245c8a1df add how to quantize doc Matt Williams 2023-10-12 15:34:57 -07:00
  • 7a537cdca9
    Merge pull request #770 from jmorganca/mxyng/fix-download Michael Yang 2023-10-12 12:56:43 -07:00
  • 257ffeb997 fix download Michael Yang 2023-10-12 12:52:35 -07:00
  • 9b513bb6b1
    Merge pull request #753 from jmorganca/mattw/examplereorg Matt Williams 2023-10-12 11:24:12 -07:00
  • 042100f797 final rename Matt Williams 2023-10-12 11:23:41 -07:00
  • 7804b8fab9
    validate api options fields from map (#711) Bruce MacDonald 2023-10-12 11:18:11 -04:00
  • 56497663c8
    relay model runner error message to client (#720) Bruce MacDonald 2023-10-12 11:16:37 -04:00
  • e1afcb8af2 simple gen to simple Matt Williams 2023-10-11 21:29:07 -07:00
  • 385eeea357 remove with Matt Williams 2023-10-11 21:26:11 -07:00
  • 8a41b244e8 add golang gen Matt Williams 2023-10-11 21:20:50 -07:00
  • 92578798bb fix relative links in README.md Jeffrey Morgan 2023-10-11 19:24:06 -04:00
  • 788637918a
    Merge pull request #760 from jmorganca/mxyng/more-downloads Michael Yang 2023-10-11 14:33:10 -07:00
  • c413a55093 download: handle inner errors Michael Yang 2023-10-11 13:49:01 -07:00
  • 630bb75d2a dynamically size download parts based on file size Michael Yang 2023-10-10 17:22:44 -07:00
  • a2055a1e93 update download Michael Yang 2023-10-09 10:14:49 -07:00
  • b599946b74 add format bytes Michael Yang 2023-10-11 10:55:07 -07:00
  • aca2d65b82
    Merge pull request #757 from jmorganca/mxyng/format-time Michael Yang 2023-10-11 11:12:29 -07:00
  • b5e08e3373 cleanup format time Michael Yang 2023-10-11 11:05:39 -07:00
  • 274d5a5fdf
    optional parameter to not stream response (#639) Bruce MacDonald 2023-10-11 12:54:27 -04:00
  • fc6b49be32 add ts alternate to python langchain simplegen Matt Williams 2023-10-11 09:50:15 -07:00
  • 77295f716e
    prevent waiting on exited command (#752) Bruce MacDonald 2023-10-11 12:32:13 -04:00
  • 615f7d1dea cleanup readme. Matt Williams 2023-10-11 06:13:29 -07:00
  • cdf5e106ae rename dirs Matt Williams 2023-10-11 06:10:24 -07:00
  • a85329f59a rename the models to be more descriptive Matt Williams 2023-10-10 17:40:02 -07:00
  • f2ba1311aa
    improve vram safety with 5% vram memory buffer (#724) Bruce MacDonald 2023-10-10 16:16:09 -04:00
  • 65dcd0ce35
    always cleanup blob download (#747) Jeffrey Morgan 2023-10-10 13:12:29 -04:00
  • 0040f543a2
    Merge pull request #743 from jmorganca/mxyng/http-proxy Michael Yang 2023-10-10 09:59:06 -07:00
  • 767f9bdbbb
    Merge pull request #585 from jmorganca/matt/examplementors Matt Williams 2023-10-09 13:58:14 -07:00
  • f7f5169c94
    Update api.md (#741) Costa Alexoglou 2023-10-09 22:01:46 +02:00
  • 2cfffea02e handle client proxy Michael Yang 2023-10-09 12:18:26 -07:00
  • f6e98334e4 handle upstream proxies Michael Yang 2023-10-09 11:42:36 -07:00
  • ab0668293c llm: fix build on amd64 Jeffrey Morgan 2023-10-06 14:39:54 -07:00
  • af4cf55884
    not found error before pulling model (#718) Bruce MacDonald 2023-10-06 16:06:20 -04:00
  • d6786f2945
    add feedback for reading model metadata (#722) Bruce MacDonald 2023-10-06 16:05:32 -04:00
  • 38dc2f79bc
    Merge pull request #626 from jmorganca/mxyng/concurrent-downloads Michael Yang 2023-10-06 13:01:29 -07:00
  • cb961c87ca
    Merge pull request #679 from jamesbraza/modelfile-docs Michael Yang 2023-10-06 12:59:45 -07:00
  • 0560b28a8d names Michael Yang 2023-10-03 17:06:13 -07:00
  • 10199c5987 replace done channel with file check Michael Yang 2023-10-03 16:52:49 -07:00
  • 288814d3e4 fix ref counts Michael Yang 2023-10-03 16:44:35 -07:00