Commit Graph

  • fbb669d7ba readme: Format install instructions Thierry 2024-10-01 19:08:16 +02:00
  • e59a836300 readme: Add table of contents Thierry 2024-10-01 19:07:20 +02:00
  • bd981cc2a5 Remove use of testify on routes_test Alex Mavrogiannis 2024-10-01 09:27:09 -07:00
  • 39a3ebcc5c
    Update README.md drunkwcodes 2024-10-01 22:50:29 +08:00
  • 93361ba4ae
    Update release.yaml kavita-rane2 2024-10-01 15:20:05 +05:30
  • 19333c9338
    Update gen_common.sh kavita-rane2 2024-10-01 14:54:38 +05:30
  • 50f0260d52
    Update release.yaml kavita-rane2 2024-10-01 14:50:53 +05:30
  • 640e2644f2
    Fixing generate failure due to global gpgsign setting wikki 2024-10-01 00:42:21 -04:00
  • af6a94af40
    rocm: improve rocm compatibility Daniele 2024-10-01 04:10:37 +02:00
  • 6c832606fd Added tests for model stop during deletion Alex Mavrogiannis 2024-09-30 15:58:24 -07:00
  • 28676d64e6 runner.go: Increase size of response channel Jesse Gross 2024-09-30 15:25:33 -07:00
  • caf3681868 runner.go: Default to classic input cache policy Jesse Gross 2024-09-25 13:12:35 -07:00
  • 19f048a1b2 runner.go: Don't re-allocate memory for every batch Jesse Gross 2024-09-30 11:31:07 -07:00
  • 8a9455f23a llama: catch up on patches Daniel Hiltgen 2024-09-30 11:29:12 -07:00
  • 192e00b39d runner.go: Image embedding cache Jesse Gross 2024-09-24 14:08:18 -07:00
  • 2744be8f43 runner.go: Export external cache members Jesse Gross 2024-09-24 14:16:56 -07:00
  • 1c39676084 runner.go: Move Unicode checking code and add tests Jesse Gross 2024-09-24 14:45:13 -07:00
  • d649e59a55 runner.go: Support for vision models Jesse Gross 2024-09-19 12:12:05 -07:00
  • 46f9325622 runner.go: More accurately capture timings Jesse Gross 2024-09-24 15:24:23 -07:00
  • 4fd6e33d6c runner.go: Don't panic when processing sequences Jesse Gross 2024-09-17 12:06:35 -07:00
  • ba8eb27ac9 runner.go: Update TODOs jmorganca 2024-09-17 13:58:44 -07:00
  • 4e0308cb48 runner.go: Simplify flushing of pending tokens Jesse Gross 2024-09-23 13:48:06 -07:00
  • 81df75ef06 runner.go: Remove stop tokens from cache Jesse Gross 2024-09-19 14:59:27 -07:00
  • a16399a833 llama.go: Don't return nil from Tokenize on zero length input Jesse Gross 2024-09-23 15:14:56 -07:00
  • 3509b022b5 runner.go: Allocate batches for all sequences during init Jesse Gross 2024-09-20 16:49:29 -07:00
  • 7ad6251988 llama: Refine developer docs for Go server (#6842) Daniel Hiltgen 2024-09-27 15:12:40 -07:00
  • 71e76f8c90 server.cpp: cleanup cross attention state jmorganca 2024-09-26 23:53:12 -07:00
  • 7d5e0ff80e add server.cpp and patches jmorganca 2024-09-26 23:04:06 -07:00
  • 4023e3a2db llama: Exercise the new build in CI (#6989) Daniel Hiltgen 2024-09-27 14:49:55 -07:00
  • ae0c6f0f50 llama: don't create extraneous directories (#6988) Daniel Hiltgen 2024-09-26 14:05:31 -07:00
  • 0db090d25e Refine go server makefiles to be more DRY (#6924) Daniel Hiltgen 2024-09-26 11:32:14 -07:00
  • 57971c630b llama: gather transitive dependencies for rocm for dist packaging (#6848) Daniel Hiltgen 2024-09-18 08:32:36 -07:00
  • 3d602d7888 doc: explain golang objc linker warning (#6830) Daniel Hiltgen 2024-09-16 14:21:35 -07:00
  • f8c11a5e66 cache: Clear old KV cache entries when evicting a slot Jesse Gross 2024-09-16 11:03:23 -07:00
  • a07f5cb509 Re-introduce the llama package jmorganca 2024-04-20 18:08:09 -04:00
  • f9ef5aabac stop model before deletion if loaded Alex Mavrogiannis 2024-09-30 10:06:44 -07:00
  • 3dd13b1bd9
    Update build_remote.py Vignesh Skanda 2024-09-30 14:43:50 +05:30
  • 79d3b1e2bd
    readme: add ARGO LLM tool to community integrations (#7027) zmldndx 2024-09-30 04:01:01 +08:00
  • a2f666e727
    Update README.md Jeffrey Morgan 2024-09-29 13:00:17 -07:00
  • 5f4ebeba95 server: add "Cache-Control: max-age=0" response header Justin Cranford 2024-09-29 04:11:13 -04:00
  • 1e96996db8 server: fix custom template capabiliy checking for generation Kyle Milner 2024-09-29 14:59:52 +10:00
  • ef96bfef30
    Update README.md zmldndx 2024-09-29 12:16:20 +08:00
  • c9089bc92f llama: Fix directory for conditional flash attention patch Jesse Gross 2024-09-27 15:43:28 -07:00
  • a52808296c
    llama: Refine developer docs for Go server (#6842) Daniel Hiltgen 2024-09-27 15:12:40 -07:00
  • cc94602ed0 llama: Refine developer docs for Go server Daniel Hiltgen 2024-09-17 12:03:42 -07:00
  • 68c4105fb7
    llama: Exercise the new build in CI (#6989) Daniel Hiltgen 2024-09-27 14:49:55 -07:00
  • 5486c57364 fix template / imageproc issues Patrick Devine 2024-09-26 22:39:45 -07:00
  • 0c0be7b35f
    Merge cd15aa029a705cdf6689bea09d6a48bbba4b1b6f into 03608cb46ecdccaf8c340c9390626a9d8fcc3c6b Leon Sander 2024-09-26 17:29:28 -04:00
  • 62d5416160 llama: Exercise the new build in CI Daniel Hiltgen 2024-09-26 14:04:24 -07:00
  • 7d4fdeca6c
    llama: don't create extraneous directories (#6988) Daniel Hiltgen 2024-09-26 14:05:31 -07:00
  • ed1d99c227 llama: don't create extraneous directories Daniel Hiltgen 2024-09-26 13:41:33 -07:00
  • 03608cb46e
    server: close response body on error (#6986) Blake Mizerany 2024-09-26 12:00:31 -07:00
  • 81bdcb8f03
    Refine go server makefiles to be more DRY (#6924) Daniel Hiltgen 2024-09-26 11:32:14 -07:00
  • fb99762a91 Refine go server makefiles to be more DRY Daniel Hiltgen 2024-09-22 09:46:15 -07:00
  • d19120f152 server: close response body on error Blake Mizerany 2024-09-26 11:16:24 -07:00
  • a2d33ee390 linter feeding Patrick Devine 2024-09-26 02:15:17 -07:00
  • 96a8b2f7d8 fix prompt for non-mllama multimodal Patrick Devine 2024-09-26 01:31:53 -07:00
  • c48e2cfc0d more fixes for mllama Patrick Devine 2024-09-26 01:16:41 -07:00
  • 22d861dfe2 update patch jmorganca/mllama jmorganca 2024-09-25 22:09:38 -07:00
  • 055cb6b0e2 update server.cpp changes jmorganca 2024-09-25 21:54:23 -07:00
  • d0c8ce5ea4 llm: add server entrypoint for mllama jmorganca 2024-09-25 14:37:28 -07:00
  • e466b29881
    fix(generate): disable gpg signing when applying git patches Maddison Hellstrom 2024-09-25 17:53:38 -07:00
  • 454118aecd Bump ROCm on linux to 6.2 Daniel Hiltgen 2024-09-25 16:06:30 -07:00
  • bc0a60f617 Adding testsa nd more descriptive erorr messages for validation William Guss 2024-09-25 13:57:16 -07:00
  • 8ac915f709 llm: add mllama language support jmorganca 2024-09-25 13:49:10 -07:00
  • 5da1043680 feed the linter Patrick Devine 2024-09-25 13:08:08 -07:00
  • f8ed545cbb image processing for llama3.2 Patrick Devine 2024-09-25 11:54:43 -07:00
  • 450acb71a6
    readme: fix llama3.1 -> llama3.2 typo (#6962) Xe Iaso 2024-09-25 11:53:47 -07:00
  • 64424503e5
    README: Fix llama3.1 -> llama3.2 typo Xe Iaso 2024-09-25 11:47:51 -07:00
  • 55ea963c9e
    update default model to llama3.2 (#6959) Jeffrey Morgan 2024-09-25 11:11:22 -07:00
  • 18210f0998 update default model to llama3.2 jmorganca 2024-09-25 10:47:41 -07:00
  • cf22ca1984 example: add example notebook on llm tracing Jannik Maierhöfer 2024-09-25 14:37:26 +02:00
  • 85f635877d
    Update openai.go William Guss 2024-09-24 23:52:26 -07:00
  • ae03496a48
    Update openai.go William Guss 2024-09-24 23:47:40 -07:00
  • dc098b4889
    Update gen_common.sh kavita-rane2 2024-09-25 10:51:49 +05:30
  • 544f770109 prompt-fix root 2024-09-25 00:57:38 -04:00
  • bcbf99633c
    Update README.md - Library - Haverscript Andy Gill 2024-09-24 19:41:35 -05:00
  • 30c631c199 runner.go: Image embedding cache Jesse Gross 2024-09-24 14:08:18 -07:00
  • 7e44cdd613 runner.go: Export external cache members Jesse Gross 2024-09-24 14:16:56 -07:00
  • cdb539cf2a runner.go: Move Unicode checking code and add tests Jesse Gross 2024-09-24 14:45:13 -07:00
  • 8e94322327 runner.go: Support for vision models Jesse Gross 2024-09-19 12:12:05 -07:00
  • 0b0b5d2b8d runner.go: More accurately capture timings Jesse Gross 2024-09-24 15:24:23 -07:00
  • e9e9bdb8d9
    CI: Fix win arm version defect (#6940) v0.3.12 Daniel Hiltgen 2024-09-24 15:18:10 -07:00
  • ddafbb1fe1 Include support for getting models from HG José Carlos García 2024-09-24 23:49:40 +02:00
  • 3737a5a669 doc: capture numeric group requirement Daniel Hiltgen 2024-09-24 14:37:32 -07:00
  • 76640cebad Filter out build artifacts from docker context Daniel Hiltgen 2024-09-24 13:47:29 -07:00
  • 09c032519e When falling back to CPU, don't send GPU flags to the runner Daniel Hiltgen 2024-09-24 11:58:45 -07:00
  • 66a7b2a893 Bubble up cuda library error codes with some retries Daniel Hiltgen 2024-09-09 12:07:27 -07:00
  • c748e00c3a CI: Fix win arm version defect Daniel Hiltgen 2024-09-24 13:37:13 -07:00
  • 35bb6d32b3
    readme: update llamaindex links (#6939) Alex Yang 2024-09-24 12:15:43 -07:00
  • 5041eae1cd
    docs: update llamaindex links Alex Yang 2024-09-24 11:44:14 -07:00
  • 9864038750 add CLI completion for commands Pranit Bauva 2024-09-24 22:43:26 +05:30
  • cd15aa029a Added Local Multimodal AI Chat link to README.md Leon-Sander 2024-09-24 13:42:24 +02:00
  • 62041fcff0 Merge branch 'main' of github.com:ollama/ollama into basic-auth kemalelmizan 2024-09-24 15:34:16 +07:00
  • 98701b58b3
    readme: add LLMChat to community integrations (#6919) Deep Lakhani 2024-09-23 20:49:46 -04:00
  • aec3771a3e runner.go: Don't panic when processing sequences Jesse Gross 2024-09-17 12:06:35 -07:00
  • e0d516a71d runner.go: Update TODOs jmorganca 2024-09-17 13:58:44 -07:00
  • 4aa0274203 runner.go: Simplify flushing of pending tokens Jesse Gross 2024-09-23 13:48:06 -07:00
  • 8758ed091d runner.go: Remove stop tokens from cache Jesse Gross 2024-09-19 14:59:27 -07:00
  • 66f7c89f08 llama.go: Don't return nil from Tokenize on zero length input Jesse Gross 2024-09-23 15:14:56 -07:00