Commit Graph

  • 6bd8a4b0a1
    Merge pull request #6064 from ollama/mxyng/convert-llama3 Michael Yang 2024-08-21 12:57:09 -07:00
  • 77903ab8b4 llama3.1 Michael Yang 2024-07-29 14:53:02 -07:00
  • e22286c9e1
    Merge pull request #5365 from ollama/mxyng/convert-gemma2 Michael Yang 2024-08-21 11:48:43 -07:00
  • 107f695929
    Merge pull request #4917 from ollama/mxyng/convert-bert Michael Yang 2024-08-21 11:48:29 -07:00
  • 4ecc70d3b4
    Merge pull request #6386 from zwwhdls/fix-new-layer Michael Yang 2024-08-21 10:58:45 -07:00
  • 236413d4b2
    Merge pull request #1 from szocsbarni/feature/add-OpenAPI3.1-spec JD Davis 2024-08-21 08:39:50 -05:00
  • e990dec90f clean venjiang 2024-08-21 18:16:41 +08:00
  • aab555d371 fix venjiang 2024-08-21 17:34:44 +08:00
  • 5f4d3c351a it's work venjiang 2024-08-20 19:32:09 +08:00
  • 58fdac78a4 function call on stream venjiang 2024-08-15 20:11:34 +08:00
  • 3546bbd08c convert gemma2 Michael Yang 2024-06-28 13:27:05 -07:00
  • beb49eef65 create bert models from cli Michael Yang 2024-06-07 14:55:56 -07:00
  • 5a28b9cf5f bert Michael Yang 2024-06-06 08:59:04 -07:00
  • f7e8565cd7
    WSL 2 is not an upgrade, it's a different type Erkin Alp Güney 2024-08-20 23:59:39 +03:00
  • ce78e400c2 trying Josh Yan 2024-08-20 13:38:33 -07:00
  • ddc3e1d573 Fix filename for non darwin arm builds Daniel Hiltgen 2024-08-13 14:33:11 -07:00
  • cddd5305e9 lint jmorganca 2024-08-13 11:24:46 -07:00
  • 37d92bba34 Add missing vendor headers to ggml sync Daniel Hiltgen 2024-08-09 16:45:18 -07:00
  • e925996e1d Wire up native source file dependencies Daniel Hiltgen 2024-08-05 08:56:47 -07:00
  • 7d1bbd901c Bump llama sync to 1e6f65 Daniel Hiltgen 2024-08-06 16:50:34 -07:00
  • 67eec045ec fix dolphin-mistral Daniel Hiltgen 2024-08-01 14:47:00 -07:00
  • cb243cc37f harden integration tests Daniel Hiltgen 2024-08-01 14:41:23 -07:00
  • 51b977b577 Runtime selection of new or old runners Daniel Hiltgen 2024-08-01 08:54:44 -07:00
  • 64def5fbb5 Implement timings response in Go server Daniel Hiltgen 2024-07-29 14:09:55 -07:00
  • efe27ee0eb Get embeddings working Daniel Hiltgen 2024-07-31 11:08:09 -07:00
  • c7cde2b745 Fix parallel requests Daniel Hiltgen 2024-07-31 15:02:58 -07:00
  • df420a9467 Update sync with latest llama.cpp layout, and run against b3485 Daniel Hiltgen 2024-07-29 16:21:09 -07:00
  • 66b7d2d3d0 Prefix all build artifacts with an OS/ARCH dir Daniel Hiltgen 2024-06-24 09:23:34 -07:00
  • 2c94356a2c Get linux building Daniel Hiltgen 2024-06-23 12:07:41 -07:00
  • cd2b932760 add note in readme jmorganca 2024-06-21 16:22:27 -04:00
  • c818e05aa3 clean up metal code jmorganca 2024-06-15 10:06:36 -07:00
  • c87d065ed6 fix Makefile on windows jmorganca 2024-06-20 21:52:10 -04:00
  • 4d89fc6a3f remove printing jmorganca 2024-06-13 18:41:12 -07:00
  • 9c0e44c7db dont apply license to stb_image.h and json.hpp jmorganca 2024-06-13 14:35:11 -07:00
  • 1245d30427 lint jmorganca 2024-06-13 14:21:55 -07:00
  • 2d69557746 update sync header jmorganca 2024-06-13 14:12:23 -07:00
  • 750c133e50 remove unused script jmorganca 2024-06-13 14:07:05 -07:00
  • 96150e1e01 fix metal jmorganca 2024-06-12 12:18:40 -07:00
  • f51ca6f2ce add header to not edit jmorganca 2024-06-12 11:40:13 -07:00
  • ad8e88c86a add header to not edit jmorganca 2024-06-12 11:38:42 -07:00
  • 52106f3adf fix build on windows jmorganca 2024-06-12 02:47:12 -04:00
  • 831bf2eefd fix Makefile jmorganca 2024-06-11 23:18:07 -07:00
  • 343af277ca fix README.md jmorganca 2024-06-11 22:54:45 -07:00
  • 42559be4e6 fix README.md jmorganca 2024-06-11 22:54:31 -07:00
  • ad9507e7c1 consistent whitespace jmorganca 2024-06-11 22:50:10 -07:00
  • 22494ea8ad update .gitattributes jmorganca 2024-06-11 22:48:06 -07:00
  • e2cf814eaa link metal jmorganca 2024-06-11 22:46:14 -07:00
  • d09929a277 wip jmorganca 2024-06-11 18:53:48 -07:00
  • 13f68db1dd wip meta jmorganca 2024-06-11 11:12:00 -07:00
  • 96d4254e18 sync jmorganca 2024-06-10 17:23:09 -07:00
  • f9fe8f7e9a remove perl docs jmorganca 2024-06-10 09:26:19 -07:00
  • be59f3ce9b remove build scripts jmorganca 2024-06-10 02:56:37 -04:00
  • 0fc21ffea8 remove need for perl jmorganca 2024-06-10 00:04:21 -04:00
  • 2c29738673 fix output jmorganca 2024-06-09 23:53:40 -04:00
  • b6c0701165 arch build jmorganca 2024-06-09 20:19:11 -07:00
  • 7c3467b795 add temporary makefile jmorganca 2024-06-09 22:33:31 -04:00
  • 0e30e1dee6 fix cuda and rocm builds jmorganca 2024-06-09 19:49:22 -04:00
  • 05b6f2d608 fix cgo flags for darwin amd64 jmorganca 2024-06-09 14:30:41 -07:00
  • 91d8f2089d remove -fPIC from build_hipblas.sh jmorganca 2024-06-07 12:52:49 -04:00
  • 6288a0872a fix issues with runner jmorganca 2024-06-07 09:32:52 -07:00
  • 66d5d8e9b2 move sync script back in for now jmorganca 2024-06-07 09:26:44 -07:00
  • c0b5accf81 llama: sync jmorganca 2024-06-07 00:27:24 -07:00
  • 5fb4c282c6 update to d5c938cd jmorganca 2024-06-07 00:15:58 -07:00
  • dac6e60790 add patches jmorganca 2024-06-06 23:55:47 -07:00
  • 7053e0bab8 cleanup stop code jmorganca 2024-06-04 00:58:58 -07:00
  • f5225761b7 fix example jmorganca 2024-06-04 00:43:03 -07:00
  • 9758536380 revert llm changes jmorganca 2024-06-04 00:40:19 -07:00
  • 4bcf775d46 num predict jmorganca 2024-05-28 23:38:44 -07:00
  • 4c718097d8 basic progress jmorganca 2024-05-28 23:11:48 -07:00
  • f28934d013 add more runner params jmorganca 2024-05-28 00:02:01 -07:00
  • 431aada64d truncate stop properly jmorganca 2024-05-27 23:09:56 -07:00
  • f4262a90e7 wip stop tokens jmorganca 2024-05-27 14:38:44 -07:00
  • 8400358bee embeddings jmorganca 2024-05-27 11:33:47 -07:00
  • 819055b99d remove dependency on llm jmorganca 2024-05-26 23:23:09 -07:00
  • b3d076470e grammar jmorganca 2024-05-26 23:14:44 -07:00
  • 5de4a49456 sampling jmorganca 2024-05-26 23:01:05 -07:00
  • dd59b27785 better example module, add port jmorganca 2024-05-25 20:11:57 -07:00
  • d7db410f28 wip jmorganca 2024-05-24 10:09:35 -07:00
  • 5683b524e6 add llava to runner jmorganca 2024-05-23 18:22:15 -07:00
  • 9b18b48892 fix output in build_hipblas.sh jmorganca 2024-05-20 16:43:53 -07:00
  • 99e6cdd71b mods to build_hipblas.sh for linux jmorganca 2024-05-20 16:15:16 -07:00
  • 9eba8cf9cf wip jmorganca 2024-05-20 15:27:10 -07:00
  • 661032601d improve cuda and hipblas build scripts jmorganca 2024-05-20 16:17:13 -04:00
  • 4ef6b5fcae cuda linux jmorganca 2024-05-19 23:11:30 -07:00
  • df09603165 Update README.md Jeffrey Morgan 2024-05-19 16:47:50 -07:00
  • 176f004204 Update README.md Jeffrey Morgan 2024-05-19 16:47:19 -07:00
  • c46b2d88ee disable log file jmorganca 2024-05-19 16:36:32 -07:00
  • fd700f8b91 fix readme for llava jmorganca 2024-05-19 16:33:37 -07:00
  • da0f918b67 add llava jmorganca 2024-05-19 16:30:11 -07:00
  • c929e61917 llama: add clip dependencies jmorganca 2024-05-19 14:06:46 -07:00
  • df272f358f add clip and parallel requests to the todo list jmorganca 2024-05-19 14:01:52 -07:00
  • a3c8cb95e7 fix cuda build jmorganca 2024-05-19 03:34:24 -04:00
  • cd86d7759f fix build on windows jmorganca 2024-05-19 03:19:41 -04:00
  • 26981c90cf fix ggml-metal.m build constraints jmorganca 2024-05-19 00:10:15 -07:00
  • e93232d653 fix ggml-metal.m jmorganca 2024-05-19 00:06:26 -07:00
  • 5a65e1f9ea avx2 should only add avx2 jmorganca 2024-05-18 23:53:29 -07:00
  • 83184df705 fix sync script jmorganca 2024-05-18 23:50:50 -07:00
  • 6b492fc9bd fix ggml-metal.m jmorganca 2024-05-18 23:34:58 -07:00
  • 89830adae0 fix ggml-metal.m jmorganca 2024-05-18 23:31:41 -07:00
  • ec3542eff2 add license headers jmorganca 2024-05-18 23:30:28 -07:00