ollama

Commit Graph

Author	SHA1	Message	Date
Jeffrey Morgan	8f8e736b13	update llama.cpp submodule to `d7fd29f` (#5475 )	2 years ago
Jeffrey Morgan	d89454de80	Use slot with cached prompt instead of least recently used (#5492 ) * Use common prefix to select slot * actually report `longest`	2 years ago
Daniel Hiltgen	af28b94533	Merge pull request #5469 from dhiltgen/prevent_system_oom Prevent loading models larger than total memory	2 years ago
Jeffrey Morgan	e9188e971a	Fix assert on small embedding inputs (#5491 ) * Fix assert on small embedding inputs * Update llm/patches/09-pooling.diff	2 years ago
Daniel Hiltgen	78eddfc068	Merge pull request #4412 from dhiltgen/win_docs Document older win10 terminal problems	2 years ago
Daniel Hiltgen	02c24d3d01	Merge pull request #5466 from dhiltgen/fix_clip_unicode Fix clip model loading with unicode paths	2 years ago
Daniel Hiltgen	52abc8acb7	Document older win10 terminal problems We haven't found a workaround, so for now recommend updating.	2 years ago
Jeffrey Morgan	4d71c559b2	fix error detection by limiting model loading error parsing (#5472 )	2 years ago
Anatoli Babenia	0d16eb310e	fix: use `envconfig.ModelsDir` directly (#4821 ) * Co-authored-by: Anatoli Babenia <anatoli@rainforce.org> Co-authored-by: Maas Lalani <maas@lalani.dev>	2 years ago
Daniel Hiltgen	8072e205ff	Merge pull request #5447 from dhiltgen/fix_keepalive Only set default keep_alive on initial model load	2 years ago
Daniel Hiltgen	955f2a4e03	Only set default keep_alive on initial model load This change fixes the handling of keep_alive so that if client request omits the setting, we only set this on initial load. Once the model is loaded, if new requests leave this unset, we'll keep whatever keep_alive was there.	2 years ago
Daniel Hiltgen	3c75113e37	Prevent loading models larger than total memory Users may not realize the siny new model they're trying to load fits on their disk, but can't load into system+GPU memory. Today we crash, but with this fix, we'll give them a better error message before even trying to load it.	2 years ago
Daniel Hiltgen	ccd7785859	Merge pull request #5243 from dhiltgen/modelfile_use_mmap Fix use_mmap for modefiles	2 years ago
royjhan	3b5a4a77f3	Return Correct Prompt Eval Count Regardless of Cache Prompt (#5371 ) * openai compatibility * Revert "openai compatibility" This reverts commit d3f98a811e00fc497d889c8c45b0cfec5b64690c. * remove erroneous subtraction of prompt cache	2 years ago
Daniel Hiltgen	daed0634a9	Merge pull request #5467 from dhiltgen/bogus_cpu_mac_error Fix corner cases on tmp cleaner on mac	2 years ago
Daniel Hiltgen	0d4dd707bc	Merge pull request #5465 from dhiltgen/better_cuda_logging Better nvidia GPU discovery logging	2 years ago
Daniel Hiltgen	0e982bc1f4	Fix corner cases on tmp cleaner on mac When ollama is running a long time, tmp cleaners can remove the runners. This tightens up a few corner cases on arm macs where we failed with "server cpu not listed in available servers map[]"	2 years ago
Daniel Hiltgen	6298f49816	Fix clip model loading with unicode paths On windows, if the model dir contained unicode characters clip models would fail to load. This fixes the file name handling in clip.cpp to support utf16 on windows.	2 years ago
Daniel Hiltgen	ef757da2c9	Better nvidia GPU discovery logging Refine the way we log GPU discovery to improve the non-debug output, and report more actionable log messages when possible to help users troubleshoot on their own.	2 years ago
Michael Yang	e5352297d9	Merge pull request #5448 from ollama/mxyng/fix-generate use model template by default	2 years ago
Michael Yang	65a5040e09	fix generate template	2 years ago
royjhan	d626b99b54	OpenAI: v1/completions compatibility (#5209 ) * OpenAI v1 models * Refactor Writers * Add Test Co-Authored-By: Attila Kerekes * Credit Co-Author Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com> * Empty List Testing * Use Namespace for Ownedby * Update Test * Add back envconfig * v1/models docs * Use ModelName Parser * Test Names * Remove Docs * Clean Up * Test name Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> * Add Middleware for Chat and List * Completions Endpoint * Testing Cleanup * Test with Fatal * Add functionality to chat test * Rename function * float types * type cleanup * cleaning * more cleaning * Extra test cases * merge conflicts * merge conflicts * merge conflicts * merge conflicts * cleaning * cleaning --------- Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com> Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	2 years ago
Michael Yang	dddb58a38b	Merge pull request #5051 from ollama/mxyng/capabilities add model capabilities	2 years ago
Michael Yang	400056e154	Merge pull request #5420 from ollama/mxyng/insecure-path err on insecure path	2 years ago
Daniel Hiltgen	d2f19024d0	Merge pull request #5442 from dhiltgen/concurrency_docs Add windows radeon concurrency note	2 years ago
Daniel Hiltgen	69c04eecc4	Add windows radeon concurreny note	2 years ago
royjhan	996bb1b85e	OpenAI: /v1/models and /v1/models/{model} compatibility (#5007 ) * OpenAI v1 models * Refactor Writers * Add Test Co-Authored-By: Attila Kerekes * Credit Co-Author Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com> * Empty List Testing * Use Namespace for Ownedby * Update Test * Add back envconfig * v1/models docs * Use ModelName Parser * Test Names * Remove Docs * Clean Up * Test name Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> * Add Middleware for Chat and List * Testing Cleanup * Test with Fatal * Add functionality to chat test * OpenAI: /v1/models/{model} compatibility (#5028) * Retrieve Model * OpenAI Delete Model * Retrieve Middleware * Remove Delete from Branch * Update Test * Middleware Test File * Function name * Cleanup * Test Update * Test Update --------- Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com> Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	2 years ago
Daniel Hiltgen	422dcc3856	Merge pull request #5439 from dhiltgen/fix_centos_7_build Switch ARM64 container image base to rocky 8	2 years ago
Daniel Hiltgen	020bd60ab2	Switch amd container image base to rocky 8 The centos 7 arm mirrors have disappeared due to the EOL 2 days ago, and the vault sed workaround which works for x86 doesn't work for arm.	2 years ago
Daniel Hiltgen	8e277b72bb	Merge pull request #5438 from dhiltgen/fix_centos_7_build Centos 7 EOL broke mirrors	2 years ago
Daniel Hiltgen	4f67b39d26	Centos 7 EOL broke mirrors As of July 1st 2024: Could not resolve host: mirrorlist.centos.org This is expected due to EOL dates.	2 years ago
Josh	2425281317	Merge pull request #5336 from ollama/jyan/from-errors fix: trim spaces for FROM argument, don't trim inside of quotes	2 years ago
Josh	0403e9860e	Merge pull request #5421 from ollama/jyan/ver fix: add unsupported architecture message for linux/windows	2 years ago
Josh Yan	33a65e3ba3	error	2 years ago
Michael Yang	88bcd79bb9	err on insecure path	2 years ago
Josh Yan	7e571f95f0	trimspace test case	2 years ago
Michael Yang	da8e2a0447	use kvs to detect embedding models	2 years ago
Michael Yang	a30915bde1	add capabilities	2 years ago
Michael Yang	58e3fff311	rename templates to template	2 years ago
Michael Yang	3f0b309ad4	remove ManifestV2	2 years ago
Daniel Hiltgen	e70610ef06	Merge pull request #5410 from dhiltgen/ctx_cleanup Fix case for NumCtx	2 years ago
Daniel Hiltgen	dfded7e075	Merge pull request #5364 from dhiltgen/concurrency_docs Document concurrent behavior and settings	2 years ago
Daniel Hiltgen	173b550438	Remove default auto from help message This may confuse users thinking "auto" is an acceptable string - it must be numeric	2 years ago
Daniel Hiltgen	cff3f44f4a	Fix case for NumCtx	2 years ago
Josh Yan	26e4e66faf	updated parsefile test	2 years ago
Daniel Hiltgen	97c9e11768	Switch use_mmap to a pointer type This uses nil as undefined for a cleaner implementation.	2 years ago
Daniel Hiltgen	3518aaef33	Merge pull request #4218 from dhiltgen/auto_parallel Enable concurrency by default	2 years ago
RAPID ARCHITECT	1963c00201	Update README.md (#5214 ) * Update README.md Added Mesop example to web & desktop * Update README.md --------- Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	2 years ago
Eduard	27402cb7a2	Update gpu.md (#5382 ) Runs fine on a NVIDIA GeForce GTX 1050 Ti	2 years ago
Jeffrey Morgan	c1218199cf	Update api.md	2 years ago

1 2 3 4 5 ...

3054 Commits (8f8e736b131510c8707bed5886b343906cb74a24) All Branches Search

3054 Commits (8f8e736b131510c8707bed5886b343906cb74a24)

All Branches