Commit Graph

  • 52ce350b7a Fix bad symbol load detection Daniel Hiltgen 2024-06-19 08:39:07 -07:00
  • 2abebb2cbe
    Merge pull request #5128 from zhewang1-intc/fix_levelzero_empty_symbol_detect Daniel Hiltgen 2024-06-19 08:33:16 -07:00
  • 97e29ac4fe
    Merge branch 'main' into cacheconfig Sam 2024-06-20 01:17:04 +12:00
  • ed6f8a56e1
    Update requirements.txt dcasota 2024-06-19 13:07:23 +02:00
  • 380e06e5be types/model: remove Digest Blake Mizerany 2024-06-18 13:29:38 -07:00
  • fd0b095cf6
    linux.md: Make it clear that ollama does not need to be installed as a service crazy2be 2024-06-18 23:12:49 -04:00
  • badf975e45 get real func ptr. Wang,Zhe 2024-06-19 09:00:51 +08:00
  • 755b4e4fc2 Revert "gpu: add env var for detecting Intel oneapi gpus (#5076)" Wang,Zhe 2024-06-19 08:59:58 +08:00
  • c22d54895a Initial Batch Embedding Roy Han 2024-06-18 17:34:36 -07:00
  • 1a1c99e334 Bump latest fedora cuda repo to 39 Daniel Hiltgen 2024-06-18 17:13:54 -07:00
  • 21adf8b6d2
    Merge pull request #5121 from ollama/mxyng/deepseekv2 v0.1.45-rc3 Michael Yang 2024-06-18 16:30:58 -07:00
  • 784bf88b0d Wire up windows AMD driver reporting Daniel Hiltgen 2024-06-18 16:22:47 -07:00
  • e873841cbb deepseek v2 graph Michael Yang 2024-06-18 12:42:37 -07:00
  • eb8022fbe6 types/model: remove Digest Blake Mizerany 2024-06-18 13:29:38 -07:00
  • 26d0bf9236
    Merge pull request #5117 from dhiltgen/fix_prediction Daniel Hiltgen 2024-06-18 11:36:51 -07:00
  • 8226fb99f1 Add a few missing server settings and sort the list Daniel Hiltgen 2024-06-18 11:27:22 -07:00
  • 359b15a597 Handle models with divergent layer sizes Daniel Hiltgen 2024-06-18 11:05:34 -07:00
  • b55958a587
    Merge pull request #5106 from dhiltgen/clean_logs Daniel Hiltgen 2024-06-18 09:24:38 -07:00
  • 7784ca33ce Tighten up memory prediction logging Daniel Hiltgen 2024-06-17 18:39:48 -07:00
  • c9c8c98bf6
    Merge pull request #5105 from dhiltgen/cuda_mmap Daniel Hiltgen 2024-06-17 17:07:30 -07:00
  • 171796791f Adjust mmap logic for cuda windows for faster model load Daniel Hiltgen 2024-06-17 12:14:42 -07:00
  • 176d0f7075
    Update import.md Jeffrey Morgan 2024-06-17 19:44:14 -04:00
  • 1b25a7b484 Move Show Test Roy Han 2024-06-17 14:55:12 -07:00
  • cc3bb98d37 Projector Check Roy Han 2024-06-17 14:51:22 -07:00
  • ab8db6ec56 Middleware Test File Roy Han 2024-06-17 14:44:03 -07:00
  • 8ed51cac37
    Merge pull request #5103 from dhiltgen/faster_win_build Daniel Hiltgen 2024-06-17 14:23:18 -07:00
  • 1b8e9770be Add metrics endpoint and request metrics amila-ku 2024-04-07 23:41:44 +01:00
  • c9e6f0542d
    Merge pull request #5069 from dhiltgen/ci_release Daniel Hiltgen 2024-06-17 13:59:37 -07:00
  • b0930626c5 Add back lower level parallel flags Daniel Hiltgen 2024-06-17 13:44:46 -07:00
  • e890be4814 Revert "More parallelism on windows generate" Daniel Hiltgen 2024-06-17 13:32:46 -07:00
  • b2799f111b Move libraries out of users path Daniel Hiltgen 2024-06-15 13:17:20 -07:00
  • 3fb4cecc07 Clean routes Roy Han 2024-06-17 13:06:12 -07:00
  • 81f301a45f Add Projector Test Roy Han 2024-06-17 13:00:46 -07:00
  • 152fc202f5
    llm: update llama.cpp commit to 7c26775 (#4896) v0.1.45-rc2 Jeffrey Morgan 2024-06-17 15:56:16 -04:00
  • 5593f485ea -DLLAMA_OPENMP=off jmorganca 2024-06-17 15:04:41 -04:00
  • 588657c158 disable LLAMA_BLAS for now jmorganca 2024-06-17 14:43:28 -04:00
  • f70491ecb6 llm: update llama.cpp submodule to 7c26775 jmorganca 2024-06-17 13:46:02 -04:00
  • 4ad0d4d6d3
    Fix a build warning (#5096) Lei Jitang 2024-06-18 02:47:48 +08:00
  • 917ab2042e Show Test File Roy Han 2024-06-17 11:31:00 -07:00
  • 1304e2e848 Tests for api/show model info Roy Han 2024-06-17 11:21:55 -07:00
  • 9b5b69c00f llm: update llama.cpp submodule to 7c26775 jmorganca/llama-cpp-7c26775 jmorganca 2024-06-17 13:46:02 -04:00
  • 1d4bdeeedf Function Name Roy Han 2024-06-17 09:38:05 -07:00
  • ca9d168ee3 Adds a note on uninstallation after install is complete Noufal Ibrahim 2024-06-17 21:21:02 +05:30
  • ecc311faff Changes uninstall script to mirror install script Noufal Ibrahim 2024-06-17 21:20:12 +05:30
  • 221f442834 feat: support setting the KV cache quant type Sam McLeod 2024-06-17 23:29:07 +10:00
  • 154d64b2ad feat: support setting the KV cache quant type Sam McLeod 2024-06-17 22:23:09 +10:00
  • 67a92d6dad Fix a build warning Lei Jitang 2024-06-17 18:05:23 +08:00
  • 7fa907efc9
    Merge 63f302a2318a633018da3373b5585b3eb70a61d2 into 163cd3e77c42aafd003b9cb884b3a51cdbaea106 苏业钦 2024-06-17 08:41:35 +08:00
  • 163cd3e77c
    gpu: add env var for detecting Intel oneapi gpus (#5076) Jeffrey Morgan 2024-06-16 20:09:05 -04:00
  • 4c2c8f93dd
    Merge pull request #5080 from dhiltgen/debug_intel_crash Daniel Hiltgen 2024-06-16 14:42:41 -07:00
  • 1643e01eb3
    Since you have llama.cpp the default timeout is 600 seconds, then we also set 600 Vyacheslav 2024-06-16 18:36:41 +03:00
  • fd1e6e0590 Add some more debugging logs for intel discovery Daniel Hiltgen 2024-06-16 07:42:52 -07:00
  • 67e474fc34
    Add Chinese translation of README sumingcheng 2024-06-16 22:02:45 +08:00
  • 7446518301
    Merge branch 'ollama:main' into main Sumingcheng 2024-06-16 21:58:28 +08:00
  • 9533f5579e
    Add: Chinese README sumingcheng 2024-06-16 21:57:57 +08:00
  • 5e4f5dc3d7 Resolve Conflicts Roy Han 2024-06-15 22:25:46 -07:00
  • 3d4f859719 Lint Roy Han 2024-06-15 22:21:06 -07:00
  • 2a6d37ac55
    Merge branch 'main' into royh-show royjhan 2024-06-15 22:16:20 -07:00
  • 48135e7b18 Update Test Roy Han 2024-06-15 22:06:33 -07:00
  • 7ccbfa4703 Merge branch 'royh-openai' into royh-retrieve royjhan 2024-06-15 22:02:21 -07:00
  • 60759c8d15 Merge branch 'main' into royh-openai royjhan 2024-06-15 21:58:03 -07:00
  • 76d5291b71 Test Names Roy Han 2024-06-15 21:44:19 -07:00
  • 3f9a020d8f Address Feedback Roy Han 2024-06-15 21:41:39 -07:00
  • 89c79bec8c
    Add ModifiedAt Field to /api/show (#5033) royjhan 2024-06-15 20:53:56 -07:00
  • c7b77004e3
    docs: add missing powershell package to windows development instructions (#5075) Jeffrey Morgan 2024-06-15 23:08:09 -04:00
  • 34e1d5ab6f fix build error jmorganca 2024-06-15 21:57:58 -04:00
  • 6e83aed28e
    Update development.md Jeffrey Morgan 2024-06-15 21:53:26 -04:00
  • cd0fb1159f
    docs: add missing instruction for powershell build Jeffrey Morgan 2024-06-15 21:52:27 -04:00
  • 7397af291c gpu: add env var for detecting intel oneapi gpus jmorganca 2024-06-15 21:46:25 -04:00
  • b6554e9b8c fix vulkan handle releasing pufferffish 2024-06-15 21:11:07 +01:00
  • 07d143f412
    Merge pull request #5058 from coolljt0725/fix_build_warning Daniel Hiltgen 2024-06-15 11:52:36 -07:00
  • a12283e2ff Implement custom github release action Daniel Hiltgen 2024-06-15 08:26:54 -07:00
  • 63f302a231 1. fixed go build . failed on LoongArch -> go.mod: replace github.com/chewxy/math32 v1.10.1 to github.com/chewxy/math32 v1.10.2-0.20240509203351, fixed https://github.com/chewxy/math32/issues/23 2. go.sum fixed; 3. llm.go add loong64 support; 4. gen_common.sh add 64bit LoongArch support; 5. gen_linux.sh add loongarch64 ISA LASX/LSX Support. 6. Fixed Please support LoongArch ISA https://github.com/ollama/ollama/issues/4552 HougeLangley 2024-06-16 01:35:04 +08:00
  • c22175716b add llmcord.py extension JakobDylanC 2024-06-15 11:49:50 -04:00
  • 4b0050cf0e
    Merge pull request #5037 from dhiltgen/faster_win_build v0.1.45-rc1 Daniel Hiltgen 2024-06-15 08:03:05 -07:00
  • 0577af98f4 More parallelism on windows generate Daniel Hiltgen 2024-06-13 17:13:01 -07:00
  • 17ce203a26
    Merge pull request #4875 from dhiltgen/rocm_gfx900_workaround Daniel Hiltgen 2024-06-15 07:38:58 -07:00
  • d76555ffb5
    Merge pull request #4874 from dhiltgen/rocm_v6_bump Daniel Hiltgen 2024-06-15 07:38:32 -07:00
  • 705e7ad2ce
    Merge 903af5c6d51807d3f3d5e1e58879e19c60bdce55 into 2786dff5d3f03a196f5e7df64795a276e237a1e9 JD Davis 2024-06-15 09:35:44 -05:00
  • 2786dff5d3
    Merge pull request #4264 from dhiltgen/show_gpu_visible_settings Daniel Hiltgen 2024-06-15 07:33:52 -07:00
  • b958cd2848
    remove cap_get_bound check DSLstandard 2024-06-15 20:19:19 +08:00
  • e3f9ca4009 fix check_perfmon len KOISHI KOMEIJI FROM TOUHOU 11 2024-06-15 20:13:15 +08:00
  • 38466f1821 fix build pufferffish 2024-06-15 12:06:43 +01:00
  • 18f3f960b0 update gpu.go pufferffish 2024-06-15 12:05:01 +01:00
  • e77ea68e11 Merge branch 'refs/heads/main' into vulkan pufferffish 2024-06-15 12:01:36 +01:00
  • 11c55fab81 fix total memory monitor pufferffish 2024-06-15 10:58:12 +01:00
  • 257364cb3c fix free memory monitor pufferffish 2024-06-15 10:52:34 +01:00
  • e4e8a5d25a fix compilation pufferffish 2024-06-15 09:44:10 +01:00
  • 724fac470f fix segfault pufferffish 2024-06-15 08:05:48 +01:00
  • 24c8840037 it builds pufferffish 2024-06-15 07:49:28 +01:00
  • 225f0d1219 gpu: Fix build warning Lei Jitang 2024-06-15 14:26:23 +08:00
  • d90009d122 feat: added export command to api JD Davis 2024-06-15 01:10:16 -05:00
  • 93c4d69daa add support in gen_linux.sh pufferffish 2024-06-15 05:42:59 +01:00
  • 9c6b049567 add support in gpu.go pufferffish 2024-06-15 05:27:14 +01:00
  • 36cf87f314
    Merge branch 'main' into main richardanaya2_2048b.Q6_K.gguf 2024-06-14 21:19:11 -07:00
  • 903af5c6d5
    fix: added visual studio generator selection to CUDA JD Davis 2024-06-14 22:19:50 -05:00
  • 8754d5807b fix: updated the windows cpu gen to select visual studio build tools. JD Davis 2024-06-14 21:24:57 -05:00
  • 913eda3245 feat: implemented a model export cli command JD Davis 2024-06-14 19:08:50 -05:00
  • 532db58311
    Merge pull request #4972 from jayson-cloude/main Daniel Hiltgen 2024-06-14 17:04:40 -07:00
  • 9357570d59 OpenAI Delete Endpoint royh-openai-delete Roy Han 2024-06-14 16:28:22 -07:00