Commit Graph

  • 3ad243466b comments Patrick Devine 2024-08-26 19:54:06 -07:00
  • 47fa0839b9
    server: clean up route names for consistency (#6524) Jeffrey Morgan 2024-08-26 19:36:11 -07:00
  • c6cf7993e6 server: cleanup route names jmorganca 2024-08-26 19:15:41 -07:00
  • eadd0408e8 llama: sync jmorganca 2024-08-26 19:02:27 -07:00
  • a13e583c49 cleanup whitespace Patrick Devine 2024-08-26 18:09:21 -07:00
  • 3c1994d0ee small change Patrick Devine 2024-07-31 15:15:33 -07:00
  • 1b2da3829d update the import docs Patrick Devine 2024-08-26 18:04:46 -07:00
  • 8a25d6fa8c runner.go: Fix deadlock if a connection is closed during decoding Jesse Gross 2024-08-26 14:20:50 -07:00
  • 0b92754a52 runner.go: Fix resource leaks when removing sequences Jesse Gross 2024-08-26 14:26:48 -07:00
  • ecf9206a99 runner.go: Separate KV cache and context sizes Jesse Gross 2024-08-23 17:27:09 -07:00
  • 020f5b7f1c runner.go: Hold mutex for entire time when processing batch Jesse Gross 2024-08-23 16:28:38 -07:00
  • 55e6683ecb runner.go: Scale batches to be processed by numParallel Jesse Gross 2024-08-23 13:44:30 -07:00
  • 2e890ab4ad
    Merge 1972b7962cc500baaad37ed3bd31c9892613956d into 0f92b19bec97198b035a7801eda14e3d48149033 ethan 2024-08-26 21:14:06 +08:00
  • d2461f0b49
    Implicit openai model parameter multiplication disabled Yaroslav 2024-08-26 12:39:24 +02:00
  • 79379daab4 fix: when tools exists, but no call function response is empty venjiang 2024-08-26 16:27:44 +08:00
  • f4f094b8a5
    Eliminate outdated and redundant 'Generate Embedding' section Pablo 2024-08-26 08:38:44 +02:00
  • 3d067095a4
    docs: add OllamaFarm to README.md presbrey 2024-08-25 23:28:44 -04:00
  • 5a67f93eae fix tests jmorganca/openai-context jmorganca 2024-08-25 12:45:51 -07:00
  • dc04f41eb7 fix linter issues jmorganca 2024-08-25 12:41:37 -07:00
  • 9899f18e18 openai: increase context window when max_tokens is provided jmorganca 2024-08-25 12:31:47 -07:00
  • e21b8aa4a4 add integration: py-gpt Marcin Szczyglinski 2024-08-25 21:14:20 +02:00
  • 8d07947788 init caitianchi 2024-08-25 14:37:47 +08:00
  • ff9304f330
    Merge d90009d122fb603518b5ca8f471cbe3086c29eb4 into 0f92b19bec97198b035a7801eda14e3d48149033 JD Davis 2024-08-25 10:06:37 +08:00
  • 0375796a54
    Make new tokenizer logic conditional (#6395) Daniel Hiltgen 2024-08-24 17:25:37 -07:00
  • 0f92b19bec
    Only enable numa on CPUs (#6484) v0.3.7 Daniel Hiltgen 2024-08-24 17:24:50 -07:00
  • 3d3014a73e fix: remove duplicated func call alwqx 2024-08-24 23:13:32 +08:00
  • dc99a40cc8 Only enable numa on CPUs Daniel Hiltgen 2024-08-23 17:05:52 -07:00
  • a33e56cddb uses input prompt Josh Yan 2024-08-23 16:29:59 -07:00
  • 69be940bf6
    gpu: Group GPU Library sets by variant (#6483) v0.3.7-rc6 Daniel Hiltgen 2024-08-23 15:11:56 -07:00
  • e6802df906 fixed patches, llava jyan/paligemma Josh Yan 2024-08-23 14:12:26 -07:00
  • 9638c24c58
    Merge pull request #5446 from ollama/mxyng/faq Michael Yang 2024-08-23 14:05:59 -07:00
  • 25d59b9856 gpu: Group GPU Library sets by variant Daniel Hiltgen 2024-08-23 14:04:59 -07:00
  • bb362caf88 update faq Michael Yang 2024-07-02 15:02:07 -07:00
  • 386af6c1a0 passthrough OLLAMA_HOST path to client Michael Yang 2024-08-23 13:16:30 -07:00
  • c631633bce paligemma demo works Josh Yan 2024-08-23 13:18:26 -07:00
  • 7de230f005 paligemma patch Roy Han 2024-08-16 11:51:23 -07:00
  • a62817d677 demo jyan/p2 Josh Yan 2024-08-23 13:01:23 -07:00
  • 0c819e167b
    convert safetensor adapters into GGUF (#6327) Patrick Devine 2024-08-23 11:29:56 -07:00
  • bbf50412b4 Make new tokenizer logic conditional Daniel Hiltgen 2024-08-16 11:54:04 -07:00
  • 7a1e1c1caf
    gpu: Ensure driver version set before variant (#6480) Daniel Hiltgen 2024-08-23 11:21:12 -07:00
  • 0b03b9c32f
    llm: Align cmake define for cuda no peer copy (#6455) Daniel Hiltgen 2024-08-23 11:20:39 -07:00
  • ade8ee9ba6 gpu: Ensure driver version set before variant Daniel Hiltgen 2024-08-23 09:33:12 -07:00
  • e7394f9bd6 llm: Align cmake define for cuda no peer copy Daniel Hiltgen 2024-08-21 15:04:43 -07:00
  • 56c670b7ed init caitianchi 2024-08-23 16:29:32 +08:00
  • a75f357602 Link Time Optimization - cabelo@opensuse.org Alessandro de Oliveira Faria (A.K.A. CABELO) 2024-08-22 23:25:04 -03:00
  • 8eecd054db Merge branch 'main' of https://github.com/rpreslar4765/ollama Ricky Bobby 2024-08-22 23:42:04 +00:00
  • a523eabd72 commit Ricky Bobby 2024-08-22 23:35:12 +00:00
  • 0c94c732c8
    Merge d9e77ef1eecf2e49a67cf9f52463eb53a1d55f21 into 90ca84172c2a98ecfd76eb7e05cd3e33e1dde507 xuyangbocn 2024-08-22 15:53:34 -07:00
  • 6759567888
    Merge e0af306bd780da74ecf18c5a25ca342f89465e5f into 90ca84172c2a98ecfd76eb7e05cd3e33e1dde507 Hasit Bhatt 2024-08-22 15:53:33 -07:00
  • 185345c902
    Merge 7b3aaeb7db7cd8c0497c24d1baf349441de25026 into 90ca84172c2a98ecfd76eb7e05cd3e33e1dde507 jing-rui 2024-08-22 15:53:11 -07:00
  • 0b5fdc4daf
    Merge 2fe945412ae3b400f8491b9834cbfb7b254263df into 90ca84172c2a98ecfd76eb7e05cd3e33e1dde507 Michael Yang 2024-08-22 15:52:00 -07:00
  • 6fdf8235dd
    Merge branch 'ollama:main' into cors frob 2024-08-23 00:11:12 +02:00
  • 90ca84172c
    Fix embeddings memory corruption (#6467) Daniel Hiltgen 2024-08-22 14:51:42 -07:00
  • 61069ae04e Tidy up some debug log cruft Daniel Hiltgen 2024-08-22 14:18:41 -07:00
  • 4c680ea894 comments Patrick Devine 2024-08-22 14:10:02 -07:00
  • 9c33cd14ce Fix embed integration test assumption Daniel Hiltgen 2024-08-22 13:06:16 -07:00
  • 8972fd221e Fix embeddings memory corruption Daniel Hiltgen 2024-08-22 12:10:28 -07:00
  • d37cc4ef01 Unit test expose all ips on host Daniel Hiltgen 2024-08-10 16:01:35 -07:00
  • 1a8a66eab9 fix llama->ggml generate define mixups Daniel Hiltgen 2024-08-09 15:22:53 -07:00
  • c04adcd3c2 Add new runner build to CI Daniel Hiltgen 2024-06-28 11:21:12 -07:00
  • 80d5e28892 integration test for request context Daniel Hiltgen 2024-06-27 09:23:15 -07:00
  • 72649d6d6c harden a few integration tests Daniel Hiltgen 2024-06-25 15:49:01 -07:00
  • b4c3679550 Add dist install logic to existing generate scripts Daniel Hiltgen 2024-06-24 15:43:02 -07:00
  • ccad0b93af add in the gemma2 adapter converter Patrick Devine 2024-08-22 13:39:10 -07:00
  • 052fccc216 gofumpt the linter Patrick Devine 2024-08-22 13:32:48 -07:00
  • f3bfce18ff
    Merge pull request #6428 from ollama/jessegross/kvshift Jesse Gross 2024-08-22 10:18:31 -07:00
  • aff5697705
    Added 'Ollama App' as community integrations JHubi1 2024-08-22 18:59:46 +02:00
  • 1de766b9cf add autogpt integration to list of community integrations Aarushi 2024-08-22 09:06:53 +01:00
  • dbf11530c1 runner.go: Support MinP parameter Jesse Gross 2024-08-21 16:13:54 -07:00
  • a88302721c runner.go: Check for incomplete UTF-8 character Jesse Gross 2024-08-15 13:07:28 -07:00
  • 2fa311569c runner.go: Implement RepeatLastN to penalize repeated tokens Jesse Gross 2024-08-20 11:21:19 -07:00
  • 886fd3da7a runner.go: Use correct JSON field names for runners Jesse Gross 2024-08-20 16:58:09 -07:00
  • 21d1ec7488 runner.go: Shift context window when KV cache space is exceeded Jesse Gross 2024-08-14 10:35:49 -07:00
  • 3404c78f9b runner.go: Don't decode if nothing has been added to the batch Jesse Gross 2024-08-14 10:32:05 -07:00
  • ab5360d9e7 llama.go: Advance though tokens when processing multiple batches Jesse Gross 2024-08-13 16:53:35 -07:00
  • f3a8a4c181 llama.go: Use dynamic buffer for TokenToPiece Jesse Gross 2024-08-19 17:54:57 -07:00
  • 7d2c52714d llama.go: Make batch memory allocation match configuration Jesse Gross 2024-08-13 11:18:02 -07:00
  • 5ff30edbea runner.go: Fix off by one in batch size check Jesse Gross 2024-08-13 10:51:50 -07:00
  • bc8427aa2f llm: Fix array out-of-bounds memory access when tokenizing Jesse Gross 2024-08-15 15:25:21 -07:00
  • c2a3eba44f runner: Initialize numPredict Jesse Gross 2024-08-13 10:38:03 -07:00
  • aa47c6f5ed server: Fix double free on runner subprocess error. Jesse Gross 2024-08-16 14:46:33 -07:00
  • 0bb656df01 llm: Fix lint Jesse Gross 2024-08-15 09:50:42 -07:00
  • 8360dc08e2 fixup Patrick Devine 2024-08-21 16:06:43 -07:00
  • 30dd74930d mid Josh Yan 2024-08-21 16:03:15 -07:00
  • 382eb5a244 move adapter to its own file Patrick Devine 2024-08-21 14:19:01 -07:00
  • 1c3481bc0b fix alpha value Patrick Devine 2024-08-20 17:31:26 -07:00
  • c8cac73d1d add unsloth/transformers base safetensors Patrick Devine 2024-08-20 16:09:45 -07:00
  • 6f49d397b4 allow gguf adapter files to be specified on the adapter line Patrick Devine 2024-08-19 18:05:40 -07:00
  • c8ec8478a1 feed the linter Patrick Devine 2024-08-15 18:16:51 -07:00
  • ab56bbe1cd rewrite the base unit test to use generated data Patrick Devine 2024-08-15 18:10:37 -07:00
  • 08c8d57dbe smaller test file Patrick Devine 2024-08-15 01:00:40 -07:00
  • 008e168217 add adapter testdata Patrick Devine 2024-08-14 18:19:07 -07:00
  • 84a2154dff add unittest + pass KV instead of baselayer Patrick Devine 2024-08-14 17:52:50 -07:00
  • 32abdce434 gofumpt the llama converter Patrick Devine 2024-08-13 15:09:28 -07:00
  • 75133d15fa swap out the converters Patrick Devine 2024-08-13 14:24:39 -07:00
  • 69804565b3 comments Patrick Devine 2024-08-13 11:57:06 -07:00
  • 2ebb43beee feed the linter Patrick Devine 2024-08-12 18:12:56 -07:00
  • 7f39bcae88 comments Patrick Devine 2024-08-12 18:00:09 -07:00
  • 484227db2d fix unittests Patrick Devine 2024-08-12 14:30:54 -07:00
  • 68b27b1e07 convert safetensor adapters into GGUF Patrick Devine 2024-08-12 14:16:05 -07:00