Commit Graph

  • be9efdb981 Merge pull request #4326 from dhiltgen/fix_integration Daniel Hiltgen 2024-05-10 14:25:59 -07:00
  • 074dc3b9d8 Integration fixes Daniel Hiltgen 2024-05-10 14:13:26 -07:00
  • 86f9b582d5 Merge pull request #4323 from dhiltgen/sort_by_free v0.1.35 Daniel Hiltgen 2024-05-10 14:12:15 -07:00
  • 4142c3ef7c Always use the sorted list of GPUs Daniel Hiltgen 2024-05-10 13:53:21 -07:00
  • 6602e793c0 Use --quantize flag and quantize api parameter (#4321) Jeffrey Morgan 2024-05-10 13:06:13 -07:00
  • ea0fdaed28 Merge pull request #4320 from ollama/mxyng/phi2-mem Michael Yang 2024-05-10 12:35:08 -07:00
  • 1eb382da5a add phi2 mem Michael Yang 2024-05-10 12:13:28 -07:00
  • bb6fd02298 Don't clamp ctx size in PredictServerFit (#4317) Jeffrey Morgan 2024-05-10 10:17:12 -07:00
  • 7e2bceceee Merge pull request #4316 from dhiltgen/more_buffer Daniel Hiltgen 2024-05-10 10:02:34 -07:00
  • 30a7d7096c Bump VRAM buffer back up Daniel Hiltgen 2024-05-10 09:15:28 -07:00
  • 200a18820e Merge pull request #4306 from ollama/mxyng/fix-routes Michael Yang 2024-05-10 08:58:16 -07:00
  • e03637176d fix(routes): skip bad manifests Michael Yang 2024-05-09 17:44:34 -07:00
  • c02db93243 omit empty done reason v0.1.35-rc1 Bruce MacDonald 2024-05-09 16:45:29 -07:00
  • ffa4d5134a Merge pull request #4305 from ollama/mxyng/typo Michael Yang 2024-05-09 16:42:09 -07:00
  • 302d7fdbf3 prune partial downloads (#4272) Jeffrey Morgan 2024-05-09 16:35:20 -07:00
  • cf442cd57e fix typo Michael Yang 2024-05-09 16:23:37 -07:00
  • 0e1ba65855 Merge pull request #4302 from ollama/mxyng/forward-env Michael Yang 2024-05-09 16:21:05 -07:00
  • 6aad333c63 Merge pull request #4298 from ollama/mxyng/log-cleanup Michael Yang 2024-05-09 16:20:57 -07:00
  • 4fcc84e67a Merge pull request #4304 from dhiltgen/signals Daniel Hiltgen 2024-05-09 15:58:44 -07:00
  • 3ae2f441e0 Fix race in shutdown logic Daniel Hiltgen 2024-05-09 15:47:02 -07:00
  • 2abb3f6424 Update README.md (#4300) Zander Lewis 2024-05-09 18:30:49 -04:00
  • ce3b212d12 only forward some env vars Michael Yang 2024-05-09 15:11:43 -07:00
  • 83d6d46e29 Merge pull request #4299 from dhiltgen/handle_vram_reporting_lag Daniel Hiltgen 2024-05-09 15:08:56 -07:00
  • 354ad9254e Wait for GPU free memory reporting to converge Daniel Hiltgen 2024-05-09 11:44:45 -07:00
  • 58876091f7 log clean up Michael Yang 2024-05-09 13:52:56 -07:00
  • dc18eee39d Merge pull request #4238 from dhiltgen/gpu_info Daniel Hiltgen 2024-05-09 14:26:58 -07:00
  • 8727a9c140 Record more GPU information Daniel Hiltgen 2024-05-07 14:54:26 -07:00
  • d0425f26cf Merge pull request #4294 from dhiltgen/harden_subprocess_reaping Daniel Hiltgen 2024-05-09 14:02:16 -07:00
  • cfa84b8470 add done_reason to the api (#4235) Bruce MacDonald 2024-05-09 13:30:14 -07:00
  • 1580ed4c06 Merge pull request #4295 from ollama/mxyng/fix-list Michael Yang 2024-05-09 11:37:34 -07:00
  • a7ee84fc31 routes: skip invalid filepaths Michael Yang 2024-05-09 11:23:22 -07:00
  • 84ac7ce139 Refine subprocess reaping Daniel Hiltgen 2024-05-09 11:10:28 -07:00
  • 788b092c49 docs: add Guix package manager in README. (#4040) tusharhero 2024-05-09 23:40:24 +05:30
  • 5cde17a096 Add PromptingTools.jl (#2192) J S 2024-05-09 17:39:05 +01:00
  • c3837eb08c Merge pull request #4289 from dhiltgen/doc_container_workarounds Daniel Hiltgen 2024-05-09 09:27:29 -07:00
  • 8cc0ee2efe Doc container usage and workaround for nvidia errors Daniel Hiltgen 2024-05-09 08:49:40 -07:00
  • d5eec16d23 use model defaults for num_gqa, rope_frequency_base and rope_frequency_scale (#1983) Jeffrey Morgan 2024-05-09 09:06:13 -07:00
  • daa1a032f7 Update langchainjs.md (#2027) Carlos Gamez 2024-05-09 11:21:03 +08:00
  • 6042e8bc57 remove bash-comparemodels example jmorganca 2024-05-08 19:49:45 -07:00
  • 920a4b0794 Merge remote-tracking branch 'upstream/main' into pr3702 Daniel Hiltgen 2024-05-08 16:44:35 -07:00
  • ee49844d09 Merge pull request #4153 from dhiltgen/gpu_verbose_response Daniel Hiltgen 2024-05-08 16:39:11 -07:00
  • 8a516ac862 Merge pull request #4241 from dhiltgen/fix_tmp_override Daniel Hiltgen 2024-05-08 15:34:22 -07:00
  • bee2f4a3b0 Record GPU usage information Daniel Hiltgen 2024-05-04 09:15:31 -07:00
  • cef45feaa4 Add preflight OPTIONS handling and update CORS config (#4086) Bruce MacDonald 2024-05-08 13:14:00 -07:00
  • 2687f02c96 Merge pull request #4265 from ollama/mxyng/fix-show-llava Michael Yang 2024-05-08 12:51:21 -07:00
  • b25976aeb8 routes: fix show llava models Michael Yang 2024-05-08 12:42:48 -07:00
  • 001f167aad Merge pull request #4261 from ollama/mxyng/fix-tag-case Michael Yang 2024-05-08 11:09:47 -07:00
  • 486a2c1d94 types/model: fix tag case Michael Yang 2024-05-08 08:47:09 -07:00
  • 88cf154483 Merge pull request #4244 from ollama/mxyng/skip-if-same Michael Yang 2024-05-07 19:03:37 -07:00
  • 8cbd3e7510 skip hidden files in list models handler (#4247) Bruce MacDonald 2024-05-07 19:01:45 -07:00
  • eeb695261f skip if same quantization Michael Yang 2024-05-07 17:44:03 -07:00
  • dc9b1111e0 fix invalid destination error message Bruce MacDonald 2024-05-07 17:35:52 -07:00
  • 06ac829e70 Fix help string for stop parameter (#2307) Tobias Gårdhus 2024-05-08 01:48:35 +02:00
  • 72700279e2 Detect noexec and report a better error Daniel Hiltgen 2024-05-07 16:46:15 -07:00
  • 5d3f7fff26 Update langchainpy.md (#4236) boessu 2024-05-08 01:36:34 +02:00
  • d77c1c5f9d api: fill up API documentation (#3596) Eli Bendersky 2024-05-07 16:27:46 -07:00
  • 2a5302a1cf Fix paste of text with line feed characters (#3043) Giuseppe Lumia 2024-05-08 00:26:07 +02:00
  • ffbd3d173f Merge pull request #3715 from ollama/mxyng/modelname-2 Michael Yang 2024-05-07 15:21:39 -07:00
  • 1e0a669f75 Merge pull request #3682 from ollama/mxyng/quantize-all-the-things Michael Yang 2024-05-07 15:20:49 -07:00
  • 527e9be058 fix: store accurate model parameter size (#4058) Bruce MacDonald 2024-05-07 14:41:53 -07:00
  • 34bea2e272 Add macai to list of Web & Desktop integrations (#3881) Renat 2024-05-07 22:31:34 +02:00
  • fe44ae3371 Update README.md (#3884) Fernando Maclen 2024-05-07 16:17:35 -04:00
  • adeb40eaf2 Merge pull request #4231 from ollama/mxyng/parser v0.1.34 Michael Yang 2024-05-07 10:48:32 -07:00
  • d7d33e5255 Merge pull request #951 from ollama/mxyng/example-fly Michael Yang 2024-05-07 10:46:24 -07:00
  • 63bc884e25 types/model: fix parser for empty values Michael Yang 2024-05-07 09:59:21 -07:00
  • ef4e095d24 Merge pull request #4232 from ollama/revert-4190-fix/golang-ci Michael Yang 2024-05-07 10:39:37 -07:00
  • 4d4f75a8a8 Revert "fix golangci workflow missing gofmt and goimports (#4190)" Michael Yang 2024-05-07 10:35:44 -07:00
  • 3f71ba406a Correct the kubernetes terminology (#3843) Mélony QIN 2024-05-07 18:53:08 +02:00
  • 88a67127d8 Update README.md to include ollama-r library (#4012) Hause Lin 2024-05-07 12:52:30 -04:00
  • f7dc7dcc64 Update .gitattributes Jeffrey Morgan 2024-05-07 09:50:19 -07:00
  • 04f971c84b fix golangci workflow missing gofmt and goimports (#4190) alwqx 2024-05-08 00:49:40 +08:00
  • 548a7df014 update list handler to use model.Name Michael Yang 2024-04-17 14:54:14 -07:00
  • 70edb9bc4d Merge pull request #4215 from ollama/mxyng/mem Michael Yang 2024-05-07 09:26:33 -07:00
  • 3f0ed03856 Update examples/flyio/README.md Michael Yang 2024-05-07 09:25:01 -07:00
  • 4736391bfb llm: add minimum based on layer size Michael Yang 2024-05-06 17:04:19 -07:00
  • 7c5330413b note on naming restrictions (#2625) CrispStrobe 2024-05-07 01:03:21 +02:00
  • 39d9d22ca3 close server on receiving signal (#4213) Jeffrey Morgan 2024-05-06 16:01:37 -07:00
  • af47413dba Add MarshalJSON to Duration (#3284) Jackie Li 2024-05-06 23:59:18 +01:00
  • b2f00aa977 close zip files Michael Yang 2024-05-06 15:27:19 -07:00
  • 6694be5e50 convert/llama: use WriteSeeker Michael Yang 2024-05-06 14:00:50 -07:00
  • f5e8b207fb s/DisplayLongest/String/ Michael Yang 2024-05-01 10:34:39 -07:00
  • d245460362 only quantize language models Michael Yang 2024-04-25 09:01:20 -07:00
  • 4d0d0fa383 no iterator Michael Yang 2024-04-25 08:53:08 -07:00
  • 7ffe45734d rebase Michael Yang 2024-04-24 15:06:47 -07:00
  • 01811c176a comments Michael Yang 2024-04-23 15:18:45 -07:00
  • a7248f6ea8 update tests Michael Yang 2024-04-16 15:37:28 -07:00
  • 9685c34509 quantize any fp16/fp32 model Michael Yang 2024-04-12 13:55:12 -07:00
  • d091fe3c21 Windows automatically recognizes username (#3214) Jeffrey Chen 2024-05-07 06:03:14 +08:00
  • ee02f548c8 Update linux.md (#3847) Mohamed A. Fouad 2024-05-06 19:02:25 -03:00
  • b08870aff3 Merge pull request #4188 from dhiltgen/use_our_lib v0.1.34-rc1 Daniel Hiltgen 2024-05-06 14:41:05 -07:00
  • 3ecae420ac Update api.md (#3945) Darinka 2024-05-07 00:39:58 +03:00
  • 4cbbf0e13b Merge pull request #4090 from dhiltgen/rocm_paths Daniel Hiltgen 2024-05-06 14:33:41 -07:00
  • 380378cc80 Use our libraries first Daniel Hiltgen 2024-05-05 17:45:43 -07:00
  • 0963c65027 Merge pull request #4208 from dhiltgen/fix_sched_test Daniel Hiltgen 2024-05-06 14:23:12 -07:00
  • ed740a2504 Fix no slots available error with concurrent requests (#4160) Jeffrey Morgan 2024-05-06 14:22:53 -07:00
  • c9f98622b1 Skip scheduling cancelled requests, always reload unloaded runners (#4189) Jeffrey Morgan 2024-05-06 14:22:24 -07:00
  • 0a954e5066 Fix stale test logic Daniel Hiltgen 2024-05-06 14:15:37 -07:00
  • aa93423fbf docs: pbcopy on mac (#3129) Adrien Brault 2024-05-06 22:47:00 +02:00
  • 01c9386267 Add BrainSoup to compatible clients list (#3473) Nurgo 2024-05-06 22:42:16 +02:00
  • af9eb36f9f Merge pull request #4135 from dhiltgen/no_physx Daniel Hiltgen 2024-05-06 13:34:00 -07:00