Commit Graph

  • d196463cde chore: add 0.6.7 main Nikesh Parajuli 2025-05-03 01:10:21 -04:00
  • 034465adc4 chore: add 0.6.6 Ashok Gelal 2025-04-19 09:25:13 -04:00
  • 59f82e4f32 chore: add 0.6.5 Ashok Gelal 2025-04-13 19:07:41 -04:00
  • f22a4870a7 chore: add 0.6.3-rc0 Ashok Gelal 2025-03-25 21:43:33 -04:00
  • b72a7d928c chore: add 0.6.0 Ashok Gelal 2025-03-12 14:35:37 -04:00
  • 194191b027 chore: add 0.5.7 Ashok Gelal 2025-01-26 00:11:57 -05:00
  • 4ccf31799a chore: add 0.5.4 Ashok Gelal 2024-12-21 16:08:27 -05:00
  • 0d6bd8de5a chore: add 0.5.1 Ashok Gelal 2024-12-07 11:43:25 -05:00
  • 753c6c5efa chore: add 0.4.1 (not-tested) Ashok Gelal 2024-11-08 22:12:17 -05:00
  • f9b5aa8ae9 chore: build 0.3.14 Ashok Gelal 2024-10-21 12:23:26 -04:00
  • ca58ff4582 add assets Ashok Gelal 2024-10-04 13:59:16 -04:00
  • c2e8cbaa14 runner.go: Check for zero length images v0.4.1-rc0 v0.4.1 Jesse Gross 2024-11-06 13:14:18 -08:00
  • 771fab1dd8 docs: update langchainpy.md with proper model name (#7527) Edward J. Schwartz 2024-11-08 12:36:17 -05:00
  • 3a5239e6bf Set macos min version for all architectures (#7579) Daniel Hiltgen 2024-11-08 09:27:04 -08:00
  • 3d25e7bf8c win: remove preview title from installer (#7529) Daniel Hiltgen 2024-11-07 14:26:47 -08:00
  • 1618700c5a Workaround buggy P2P ROCm copy on windows (#7466) Daniel Hiltgen 2024-11-07 14:26:31 -08:00
  • b111aa5a91 Debug logging for nvcuda init (#7532) Daniel Hiltgen 2024-11-07 14:25:53 -08:00
  • 9e83e550e1 Align rocm compiler flags (#7467) Daniel Hiltgen 2024-11-07 10:20:50 -08:00
  • fc2a0715df Be explicit for gpu library link dir (#7560) Daniel Hiltgen 2024-11-07 09:20:40 -08:00
  • 3020d2dc58 docs: OLLAMA_NEW_RUNNERS no longer exists Jesse Gross 2024-11-06 13:38:57 -08:00
  • a909417602 runner.go: Remove unused arguments Jesse Gross 2024-10-30 16:54:49 -07:00
  • 6cd566872b sched: Lift parallel restriction for multimodal models except mllama Jesse Gross 2024-10-30 17:09:42 -07:00
  • 9d71bcc3e2 Update README.md (#7516) v0.4.0 RAPID ARCHITECT 2024-11-05 17:07:25 -06:00
  • a4c70fe157 One corrupt manifest should not wedge model operations (#7515) Daniel Hiltgen 2024-11-05 14:21:45 -08:00
  • 34a75102f7 prompt: Use a single token when estimating mllama context size Jesse Gross 2024-11-04 17:30:20 -08:00
  • 4157d1f7b6 readme: add Hexabot to the list of community integrations Med Marrouchi 2024-11-05 18:06:38 +01:00
  • 4ebfa2cb91 Quiet down debug log of image payload (#7454) Daniel Hiltgen 2024-11-04 13:05:16 -08:00
  • 046054fa3b CI: Switch to v13 macos runner (#7498) v0.4.0-rc8 Daniel Hiltgen 2024-11-04 13:02:07 -08:00
  • 95483f348b CI: matrix strategy fix (#7496) v0.4.0-rc7 Daniel Hiltgen 2024-11-04 10:48:35 -08:00
  • f247a6233e Merge pull request #7456 from ollama/mxyng/llama3.2-vision-mem Michael Yang 2024-11-04 09:48:43 -08:00
  • 44bd9e5994 Sign windows arm64 official binaries (#7493) Daniel Hiltgen 2024-11-04 09:15:14 -08:00
  • 18237be9b2 readme: add TextCraft to community integrations (#7377) suncloudsmoon 2024-11-03 16:53:51 -08:00
  • 29ab9fa7d7 nvidia libs have inconsistent ordering (#7473) Daniel Hiltgen 2024-11-02 16:35:41 -07:00
  • b8d5036e33 CI: omit unused tools for faster release builds (#7432) Daniel Hiltgen 2024-11-02 13:56:54 -07:00
  • 312d9de1d1 llama: Improve error handling Jesse Gross 2024-11-01 15:50:53 -07:00
  • a103dae01e runner.go: Only allocate 1 element embedding batches for mllama Jesse Gross 2024-11-01 14:29:57 -07:00
  • d07cf41a97 refactor kv estimation Michael Yang 2024-10-31 13:46:30 -07:00
  • 8c238e70ab mllama cross attention Michael Yang 2024-10-31 13:40:06 -07:00
  • 8a9bb0d000 Add basic mllama integration tests (#7455) Daniel Hiltgen 2024-10-31 17:25:48 -07:00
  • 26acdcf44e runner.go: Don't set cross attention before sending embeddings Jesse Gross 2024-10-31 10:55:31 -07:00
  • 921779bb10 Give unicode test more time to run (#7437) Daniel Hiltgen 2024-10-31 13:35:31 -07:00
  • 16f4eabe2d Refine default thread selection for NUMA systems (#7322) v0.4.0-rc6 Daniel Hiltgen 2024-10-30 15:05:45 -07:00
  • c826e57475 runner.go: Better abstract vision model integration Jesse Gross 2024-10-11 15:34:01 -07:00
  • 712e99d477 Soften windows clang requirement (#7428) Daniel Hiltgen 2024-10-30 12:28:36 -07:00
  • b754f5a6a3 Remove submodule and shift to Go server - 0.4.0 (#7157) Daniel Hiltgen 2024-10-30 10:34:28 -07:00
  • a805e5947e Move windows app out of preview (#7347) Daniel Hiltgen 2024-10-30 09:24:59 -07:00
  • 91dfbb1bba windows: Support alt install paths, fit and finish (#6967) Daniel Hiltgen 2024-10-30 09:24:31 -07:00
  • db1842b9e1 add more tests for getting the optimal tiled canvas (#7411) Patrick Devine 2024-10-29 16:28:02 -07:00
  • c9ca386131 Switch windows to clang (#7407) Daniel Hiltgen 2024-10-29 13:15:04 -07:00
  • 078f666f73 tests: Add test for Unicode processing Jesse Gross 2024-10-23 15:28:30 -07:00
  • de1557a0dc runner.go: Better handle return NULL values from llama.cpp Jesse Gross 2024-10-22 14:57:46 -07:00
  • 084929c293 add mllama image processing to the generate handler (#7384) Patrick Devine 2024-10-28 13:51:19 -07:00
  • abd5dfd06a Bump to latest Go 1.22 patch (#7379) Daniel Hiltgen 2024-10-26 17:03:37 -07:00
  • 099f7077a1 Fix deepseek deseret regex (#7369) Daniel Hiltgen 2024-10-26 14:58:54 -07:00
  • d7c94e0ca6 Better support for AMD multi-GPU on linux (#7212) Daniel Hiltgen 2024-10-26 14:04:14 -07:00
  • 35ec7f079f Fix unicode output on windows with redirect to file (#7358) Daniel Hiltgen 2024-10-25 13:43:16 -07:00
  • 5231ae52d9 Fix incremental build file deps (#7361) Daniel Hiltgen 2024-10-25 11:50:45 -07:00
  • 3085c47bea Improve dependency gathering logic (#7345) Daniel Hiltgen 2024-10-24 09:51:53 -07:00
  • 8de8729e35 Remove llama.cpp submodule and shift new build to top v0.4.0-rc5 Daniel Hiltgen 2024-10-09 13:52:36 -07:00
  • 4e988ad5d6 Move Go code out of llm package Daniel Hiltgen 2024-10-08 13:54:25 -07:00
  • 0ccc73251a fix #7247 - invalid image input (#7249) Bill Wang 2024-10-24 04:31:04 +11:00
  • dc6fe82051 integration: harden embedding test (#7306) Daniel Hiltgen 2024-10-22 15:25:22 -07:00
  • d78fb62056 default to "FROM ." if a Modelfile isn't present (#7250) Patrick Devine 2024-10-22 13:32:24 -07:00
  • 5c44461ccf Fix rocm windows build and clean up dependency gathering (#7305) Daniel Hiltgen 2024-10-22 12:54:15 -07:00
  • 03e40efa51 runner.go: Merge partial unicode characters before sending Jesse Gross 2024-10-21 11:07:19 -07:00
  • 23f746508d readme: add Ollama for Swift to the community integrations (#7295) Mattt 2024-10-21 22:29:11 -07:00
  • 48708ca0d5 server: allow vscode-webview origin (#7273) Jeffrey Morgan 2024-10-19 17:06:41 -04:00
  • c7cb0f0602 image processing for llama3.2 (#6963) Patrick Devine 2024-10-18 16:12:35 -07:00
  • bf4018b9ec llama: Decouple patching script from submodule (#7139) Daniel Hiltgen 2024-10-17 15:03:09 -07:00
  • f86d00cd95 llama: add compiler tags for cpu features (#7137) Daniel Hiltgen 2024-10-17 13:43:20 -07:00
  • f2890a4494 IBM granite/granitemoe architecture support (#6760) v0.3.14-rc0 v0.3.14 Gabe Goodhart 2024-10-17 12:59:52 -06:00
  • 05cd82ef94 Rename gpu package discover (#7143) Daniel Hiltgen 2024-10-16 17:45:00 -07:00
  • 7d6eb0d4c3 Move macos v11 support flags to build script (#7203) Daniel Hiltgen 2024-10-16 12:49:46 -07:00
  • 24636dfa87 Discovery CPU details for default thread selection (#6264) Daniel Hiltgen 2024-10-15 11:36:08 -07:00
  • 1d7fa3ad2d Adding 'Ollama App' as community integrations (#6465) JHubi1 2024-10-15 18:57:32 +02:00
  • 09035b71cd Add missing BF16 tensor type. (#7193) frob 2024-10-15 02:06:35 +02:00
  • f3c8b898cd Track GPU discovery failure information (#5820) Daniel Hiltgen 2024-10-14 16:26:45 -07:00
  • 5dd0477fd4 Fix regression on older macos versions (#7192) Daniel Hiltgen 2024-10-13 10:47:42 -07:00
  • c3d321d405 llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174) Daniel Hiltgen 2024-10-12 09:56:49 -07:00
  • 7fe3902552 cli: Send all images in conversation history v0.3.13 Jesse Gross 2024-10-09 20:46:27 -07:00
  • 0077e22d52 runner.go: Handle truncation of tokens for stop sequences Jesse Gross 2024-10-09 16:12:23 -07:00
  • 03408f3437 server: Don't clear cmd when closing a server Jesse Gross 2024-10-09 16:55:34 -07:00
  • cd7e01e8b9 fix vendoring attribute for metal (#7156) Daniel Hiltgen 2024-10-09 15:22:36 -07:00
  • 7a962bd802 fix vendoring attribute (#7155) Daniel Hiltgen 2024-10-09 14:21:02 -07:00
  • f9584deba5 Fix build leakages (#7141) Daniel Hiltgen 2024-10-08 13:04:59 -07:00
  • 96efd9052f Re-introduce the llama package (#5034) Jeffrey Morgan 2024-10-08 11:53:54 -04:00
  • de982616f1 readme: replace stale links to LangChain documentation (#7117) Shifra Goldstone 2024-10-07 21:16:56 -04:00
  • defbf9425a readme: add G1 to list of community integrations (#7096) hidden1nin 2024-10-05 14:57:53 -04:00
  • f40bb398f6 Stop model before deletion if loaded (fixed #6957) (#7050) Alex Mavrogiannis 2024-10-01 15:45:43 -07:00
  • 79d3b1e2bd readme: add ARGO LLM tool to community integrations (#7027) zmldndx 2024-09-30 04:01:01 +08:00
  • 03608cb46e server: close response body on error (#6986) Blake Mizerany 2024-09-26 12:00:31 -07:00
  • 450acb71a6 readme: fix llama3.1 -> llama3.2 typo (#6962) Xe Iaso 2024-09-25 11:53:47 -07:00
  • 55ea963c9e update default model to llama3.2 (#6959) Jeffrey Morgan 2024-09-25 11:11:22 -07:00
  • e9e9bdb8d9 CI: Fix win arm version defect (#6940) v0.3.12 Daniel Hiltgen 2024-09-24 15:18:10 -07:00
  • 35bb6d32b3 readme: update llamaindex links (#6939) Alex Yang 2024-09-24 12:15:43 -07:00
  • 98701b58b3 readme: add LLMChat to community integrations (#6919) Deep Lakhani 2024-09-23 20:49:46 -04:00
  • ad935f45ac examples: use punkt_tab instead of punkt (#6907) v0.3.12-rc5 Mahesh Sathiamoorthy 2024-09-22 07:25:28 +05:30
  • dbba73469d runner: Set windows above normal priority (#6905) Daniel Hiltgen 2024-09-21 16:54:49 -07:00
  • 6c2eb73a70 Fix missing dep path on windows CPU runners (#6884) Daniel Hiltgen 2024-09-21 16:28:29 -07:00
  • 2a038c1d7e CI: win arm artifact dist dir (#6900) v0.3.12-rc4 Daniel Hiltgen 2024-09-20 19:16:18 -07:00