Commit Graph

  • 4e262eb2a8
    remove GGML_CUDA_FORCE_MMQ=on from build (#5588) Jeffrey Morgan 2024-07-10 13:17:13 -07:00
  • a548eb6003 a8db2a9 jyan/quant3 Josh Yan 2024-07-10 13:10:58 -07:00
  • f92818d90d patch again Josh Yan 2024-07-10 13:06:40 -07:00
  • 1ef59057d0 patch llama.cpp Josh Yan 2024-07-10 13:02:37 -07:00
  • 4cfcbc328f
    Merge pull request #5124 from dhiltgen/amd_windows Daniel Hiltgen 2024-07-10 12:50:23 -07:00
  • 79292ff3e0
    Merge pull request #5555 from dhiltgen/msvc_deps Daniel Hiltgen 2024-07-10 12:50:02 -07:00
  • 8ea500441d
    Merge pull request #5580 from dhiltgen/cuda_overhead Daniel Hiltgen 2024-07-10 12:47:31 -07:00
  • b50c818623
    Merge pull request #5607 from dhiltgen/win_rocm_v6 Daniel Hiltgen 2024-07-10 12:47:10 -07:00
  • 106fe6b4ae patch Josh Yan 2024-07-10 10:29:41 -07:00
  • 5fd359d117 added patch Josh Yan 2024-07-10 10:28:42 -07:00
  • b0e4e8d76c change Josh Yan 2024-07-10 09:58:30 -07:00
  • e59453982d logs Josh Yan 2024-07-09 17:12:02 -07:00
  • 369113970a wooh Josh Yan 2024-07-09 17:04:33 -07:00
  • 26ed829415 test Josh Yan 2024-07-09 17:02:34 -07:00
  • 542134bf50 new Josh Yan 2024-07-09 16:52:47 -07:00
  • 9e0b8f1fe2 another change Josh Yan 2024-07-09 16:47:59 -07:00
  • c498609ba3 cast Josh Yan 2024-07-09 16:36:37 -07:00
  • c800a67f1b cast Josh Yan 2024-07-09 16:08:06 -07:00
  • dfc62648f3 cast Josh Yan 2024-07-09 16:05:07 -07:00
  • 24e8292e94 new changes Josh Yan 2024-07-09 15:50:41 -07:00
  • c63b4ecbf7 quantize Josh Yan 2024-07-09 15:35:44 -07:00
  • ee2b9b076c stop spinner Josh Yan 2024-07-09 11:19:54 -07:00
  • bec9100f32 tensor count Josh Yan 2024-07-09 11:02:58 -07:00
  • 1344843515 image Josh Yan 2024-07-09 10:27:33 -07:00
  • e87eafe5cd quantize percentage Josh Yan 2024-07-08 14:51:58 -07:00
  • 6bab0e2368 lint Josh Yan 2024-07-10 12:36:32 -07:00
  • b99e750b62
    Merge pull request #5605 from dhiltgen/merge_glitch Daniel Hiltgen 2024-07-10 11:47:08 -07:00
  • c4cccaf936 remove rebase err Josh Yan 2024-07-10 11:37:55 -07:00
  • 9fe5c393e4 hi Josh Yan 2024-07-09 11:36:00 -07:00
  • 007c988dba rmv double msg Josh Yan 2024-07-09 11:12:38 -07:00
  • 91d21e7c7b rmv double msg Josh Yan 2024-07-09 11:06:28 -07:00
  • 3e64284f69 percent Josh Yan 2024-07-08 11:03:44 -07:00
  • 39910f2ab2 percent Josh Yan 2024-07-05 16:49:57 -07:00
  • 96d0cd92f2 rebase Josh Yan 2024-07-10 11:31:53 -07:00
  • 3a724a7c80 isLocal firstdraft Josh Yan 2024-07-05 14:18:25 -07:00
  • f520f0056e rm config Josh Yan 2024-07-03 17:05:22 -07:00
  • d25f85ede4 on disk copy Josh Yan 2024-07-02 12:14:18 -07:00
  • b48420b74b percent Josh Yan 2024-07-05 13:23:15 -07:00
  • 784958a1cb transfer data Josh Yan 2024-07-03 17:44:23 -07:00
  • ae65cc8dea progress Josh Yan 2024-07-03 11:22:23 -07:00
  • a037528bba lint Josh Yan 2024-07-08 10:54:37 -07:00
  • 04bf41deb5 clean Josh Yan 2024-07-08 10:43:21 -07:00
  • c23cec9547 removed cmt and prints Josh Yan 2024-07-08 10:37:35 -07:00
  • 8377dc48d0 removed client isLocal() Josh Yan 2024-07-08 10:33:47 -07:00
  • 3aee405dfa lint Josh Yan 2024-07-05 16:23:39 -07:00
  • 9b3f47b674 lint Josh Yan 2024-07-05 16:16:15 -07:00
  • f5441f01a2 lint Josh Yan 2024-07-05 16:12:43 -07:00
  • ab165df43a syscopy windows Josh Yan 2024-07-05 16:09:10 -07:00
  • 79cc4c9585 os copy Josh Yan 2024-07-05 15:44:49 -07:00
  • bc3f59a6ad rmv prints Josh Yan 2024-07-05 15:14:09 -07:00
  • 1a85cb904c local copy Josh Yan 2024-07-05 15:05:58 -07:00
  • 10ea0987e9 isLocal firstdraft Josh Yan 2024-07-05 14:18:25 -07:00
  • 413d368a6a clean Josh Yan 2024-07-03 17:07:59 -07:00
  • cabf375059 rm bench Josh Yan 2024-07-03 17:06:56 -07:00
  • ca0ee1d4fe rm config Josh Yan 2024-07-03 17:06:19 -07:00
  • 1142999aab rm config Josh Yan 2024-07-03 17:05:22 -07:00
  • 0d5a72aba9 clean Josh Yan 2024-07-03 17:04:20 -07:00
  • ea837412c2 local path Josh Yan 2024-07-03 17:01:09 -07:00
  • 736ad6f438 still works Josh Yan 2024-07-03 16:43:40 -07:00
  • 64607d16a5 working Josh Yan 2024-07-03 16:31:53 -07:00
  • a6cfe7f00b benchmark Josh Yan 2024-07-02 14:53:54 -07:00
  • c3b411a515 on disk copy Josh Yan 2024-07-02 12:14:18 -07:00
  • 928f37e3ae start tests Josh Yan 2024-07-02 10:41:31 -07:00
  • 1f50356e8e Bump ROCm on windows to 6.1.2 Daniel Hiltgen 2024-07-10 11:01:22 -07:00
  • cdb9fe9b06 test values Roy Han 2024-07-10 09:57:36 -07:00
  • 22c81f62ec Remove duplicate merge glitch Daniel Hiltgen 2024-07-10 09:01:33 -07:00
  • 2d23119bc8 remove GGML_CUDA_FORCE_MMQ=on from build jmorganca 2024-07-09 20:06:50 -07:00
  • 8fefc7b63a
    Update README.md emrgnt-cmplxty 2024-07-09 20:03:39 -07:00
  • e27eac97a4
    Create SECURITY.md Jeff Larson 2024-07-09 16:25:17 -07:00
  • 73e2c8f68f Fix context exhaustion integration test for small gpus Daniel Hiltgen 2024-07-09 15:28:25 -07:00
  • 8f6d0242b6 refactoring Roy Han 2024-07-09 16:19:02 -07:00
  • f4408219e9 Refine scheduler unit tests for reliability Daniel Hiltgen 2024-07-05 15:30:06 -07:00
  • c697eb2a9b fix hanging on single string Roy Han 2024-07-09 15:51:55 -07:00
  • 2d1e3c3229
    Merge pull request #5503 from dhiltgen/dual_rocm Daniel Hiltgen 2024-07-09 15:44:16 -07:00
  • 001936569a add test Roy Han 2024-07-09 14:14:40 -07:00
  • bef534e883
    Merge branch 'main' into royh-vision royjhan 2024-07-09 14:04:09 -07:00
  • 4918fae535
    OpenAI v1/completions: allow stop token list (#5551) royjhan 2024-07-09 14:01:26 -07:00
  • b686ac144c merge conflicts Roy Han 2024-07-09 14:00:13 -07:00
  • 906203af77 add stop test Roy Han 2024-07-09 13:55:34 -07:00
  • 9803df7a35 stop token parsing fix Roy Han 2024-07-08 14:50:08 -07:00
  • 0aff67877e
    separate request tests (#5578) royjhan 2024-07-09 13:48:31 -07:00
  • 786848dfd3
    Merge branch 'main' into royh-batchembed royjhan 2024-07-09 13:48:06 -07:00
  • 6c60968806
    Merge branch 'ollama:main' into iliass/fix-InvalidRangeExpr Iliass Tiendrebeogo 2024-07-09 13:46:05 -07:00
  • fb390b8902 embedding type 64 Roy Han 2024-07-09 13:41:48 -07:00
  • bcb63e6e0e touches Roy Han 2024-07-09 13:37:00 -07:00
  • a043647bb7 Remove nested runner payloads from linux Daniel Hiltgen 2024-07-08 12:50:11 -07:00
  • f6f759fc5f Detect CUDA OS Overhead Daniel Hiltgen 2024-07-09 10:27:53 -07:00
  • 9544a57ee4
    Merge pull request #5579 from dhiltgen/win_static_deps Daniel Hiltgen 2024-07-09 12:21:13 -07:00
  • 6986030b62 flattening and smaller image Roy Han 2024-07-09 11:46:53 -07:00
  • b51e3b63ac Statically link c++ and thread lib Daniel Hiltgen 2024-07-09 11:17:44 -07:00
  • 3356e4eaf7 separate request tests Roy Han 2024-07-09 11:12:06 -07:00
  • 6bbbc50f10
    Merge pull request #5440 from ollama/mxyng/messages-templates Michael Yang 2024-07-09 09:36:32 -07:00
  • 9bbddc37a7
    Merge pull request #5126 from ollama/mxyng/messages Michael Yang 2024-07-09 09:20:44 -07:00
  • 75b44ecd7a
    Update README.md Kevin Brake 2024-07-09 12:38:37 -02:30
  • fd86b81b1f
    Create SECURITY.md Senipostol 2024-07-09 16:54:39 +03:00
  • e83132d8b3 Fix cannot range over constant Iliass tiendrebeogo 2024-07-09 01:52:38 -07:00
  • a1eabd8997 feat: compatible with openai embedding api lu.bai1 2024-07-09 16:34:47 +08:00
  • d18c8ff399
    Merge 58bd71b14d2d3d45d5854c10bc6075cacc67e1a6 into e4ff73297db2f53f1ea4b603df5670c5bde6a944 R0CKSTAR 2024-07-09 13:40:41 +08:00
  • e4ff73297d
    server: fix model reloads when setting OLLAMA_NUM_PARALLEL (#5560) v0.2.1 Jeffrey Morgan 2024-07-08 22:32:15 -07:00
  • bfbaa8285b undo some changes jmorganca 2024-07-08 22:16:13 -07:00