Commit graph

670 commits

Author SHA1 Message Date
Daniel Hiltgen
afc7c06022
install: support preview channel (#19801)
* install: support preview channel

Allow install.sh and install.ps1 to select preview artifacts with
OLLAMA_CHANNEL=preview. Stable remains the default, OLLAMA_VERSION retains
precedence, and unsupported channels are rejected.

* address comments
2026-11-20 14:47:25 -08:00
Daniel Hiltgen
0b243a141a
mlxrunner: choose default parallelism from available memory (#19785)
When OLLAMA_NUM_PARALLEL is unset, select 1, 2, 4 or 8 slots
using available memory and estimated per-client storage at the
model's context limit.

Preserve explicit settings and retain the serial default under
memory pressure, for unknown cache layouts and on other backends.
2026-11-20 07:13:42 -08:00
J Berg
5632619189
Map disabled thinking to the models lowest supported level (#19684) 2026-11-12 15:03:07 -08:00
J Berg
361b3e17fd
Support deferred tool loading in claude code (#19578) 2026-11-12 13:24:56 -08:00
anra8571
04494de5b2 docs: merging to remove retired model recommendations 2026-11-06 15:21:50 -08:00
Daniel Hiltgen
f067033f91
mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
Jeffrey Morgan
675150d6ad
voice: add voice catalog for Phonon (#19242)
* mlxrunner: import and list Phonon catalog voices

* docs: document Phonon voices
2026-10-23 16:15:08 -07:00
Jeffrey Morgan
547b98ea13
mlxrunner: spell out symbols, numbers and links for Phonon (#19234)
* mlxrunner: spell out symbols, numbers and links for Phonon

* docs: describe speech text normalization

* mlxrunner: fix Phonon misreadings inherited from xn-ptts

* mlxrunner: fix remaining Phonon misreadings

* mlxrunner: fold Phonon letters from the vocab, read #, _ and lists

* mlxrunner: add xn-ptts license notice for Phonon

* mlxrunner: move the xn-ptts license notice into normalize.go

* mlxrunner: fix remaining Phonon readings and port elongations

* docs: speech reads times and numeric dates

* mlxrunner: fix Phonon readings found in a listening pass

* docs: speech reads times and dates as written
2026-10-23 16:12:15 -07:00
Daniel Hiltgen
5e31438d5d
Support GA Gradium Phonon checkpoints (#19227)
Replace the prerelease checkpoint path with Gradium's GA format, including default-voice import and speech conditioning. Set the 0.40.9 minimum, update the speech docs, and test import, inference setup, and rejection of the old checkpoint.
2026-10-22 15:51:43 -07:00
Jeffrey Morgan
6ef847b8fe
mlxrunner: add Phonon text-to-speech support (#19166)
* mlxrunner: add Phonon text-to-speech support

Add Phonon text-to-speech through the existing MLX runner, with an
OpenAI-compatible speech endpoint and CLI playback.

Include model loading, text preprocessing, streaming audio, and
regression tests.

* docs: add speech models

* fix min version

---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2026-10-22 11:36:42 -07:00
Daniel Hiltgen
36a6e994d2
api: populate show renderer/parser fields and add template_source (#19095)
ShowResponse's renderer and parser fields existed but the server never
set them; they now carry the effective values (renderer resolves the
gemma4 legacy alias by model size). A new template_source names what
actually renders chat prompts: the configured renderer/parser (leaving
any packaged template inert), a Go template layer, the GGUF's embedded
jinja, harmony, or none.

The CLI prints renderer/parser/template source rows only when set, so
ollama show output is unchanged for models without rendering config.
2026-10-17 17:31:52 -07:00
Devon Rifkin
2476d5ead1
docs: add model grouping to cloud usage (#19069)
* docs: add model grouping to cloud usage

Document group_by=model in the cloud usage guide and OpenAPI schema.
Explain group selection and remainder, and show responses with multiple
models across time buckets.

* Update docs/api/cloud-usage.mdx

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2026-10-16 16:01:01 -07:00
Jonathan Berg
370c9b6739 cleanup 2026-10-15 16:01:26 -07:00
Jonathan Berg
2517921068 be more precise with wording 2026-10-15 14:04:57 -07:00
Jonathan Berg
3d418367d9 clef cloud launch 2026-10-15 13:34:02 -07:00
Anna Rahn
d81332c7f8
Merge branch 'main' into docs_restructuring 2026-10-13 17:20:20 -07:00
Anna Rahn
8718c2bd23
docs: Merge pull request #18981 from ollama/cloud_recommended_models_wording
docs: model recs and language standardization
2026-10-13 17:17:11 -07:00
Jeffrey Morgan
7a5ae12ead
cli: add decision model support to ollama run (#18962) 2026-10-13 12:39:05 -07:00
Anna Rahn
33a3afa604 docs: changing model recs to Models page link, updating references to Ollamas cloud 2026-10-13 10:05:39 -07:00
Anna Rahn
57d7a7df42 docs: restructuring to separate out cloud features while preserving the top-nav 2026-10-12 17:22:04 -07:00
Jeffrey Morgan
8583859ea6
Revert "docs: restructuring" (#18960) 2026-10-12 13:07:13 -07:00
Anna Rahn
c9e601e59b
Merge pull request #18828 from ollama/docs_update
docs: restructuring
2026-10-12 11:02:20 -07:00
Anna Rahn
735696814b typo in docs 2026-10-12 11:02:05 -07:00
Parth Sareen
6eaad72953
launch: populate Codex model picker with installed Ollama models (#18887) 2026-10-12 10:52:41 -07:00
Jeffrey Morgan
adc4aae9d6 llama: update to b11521 and use native decision support 2026-10-11 23:25:23 -07:00
Jeffrey Morgan
1ba3c76bd4 decision: align request validation and option descriptions 2026-10-11 23:25:23 -07:00
Anna Rahn
db2635b54b standardizing language referring to cloud services 2026-10-08 15:12:00 -07:00
Anna Rahn
8d978f6874
Merge branch 'main' into docs_update 2026-10-07 12:24:17 -07:00
Anna Rahn
539c4a07a5 re-ordering top nav, splitting out sample project into new PR 2026-10-07 12:15:54 -07:00
Anna Rahn
9062a9a2e6 removing repetition, fixing a typo 2026-10-07 12:11:19 -07:00
Anna Rahn
79f7e33058 changing wording 2026-10-07 12:00:49 -07:00
Anna Rahn
1f51984dc3 keeping old urls, updating model retirement page 2026-10-07 10:00:44 -07:00
Devon Rifkin
f864601538
server: proxy cloud usage and balance APIs (#18829)
Forward GET /api/usage and GET /api/balance through the local server
using the signed-in account.

Add API documentation and tests for proxying, signing, and
disabled cloud access.
2026-10-06 18:31:54 -07:00
Anna Rahn
266790cffe Merge remote-tracking branch 'origin/main' into docs_update
# Conflicts:
#	docs/api/introduction.mdx
#	docs/cloud.mdx
#	docs/docs.json
#	docs/guide/capabilities/decision.mdx
#	docs/index.mdx
#	docs/integrations/cline.mdx
#	docs/quickstart.mdx
2026-10-06 16:43:59 -07:00
Anna Rahn
8ca05a6027 reorganizing the docs folder, adding error handling to the sample project, changing wording 2026-10-06 16:35:27 -07:00
Anna Rahn
cba2a9cd52 documentation re-structuring 2026-10-06 12:28:15 -07:00
Patrick Devine
efe43c5561
model: add multimodal embeddings (#18820)
Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer
bidirectional text encoder with PLE, shared gemma4 vision/audio towers,
mean-pool + L2 output. /api/embed accepts per-item media via input dicts.
2026-10-06 08:08:38 -07:00
Daniel Hiltgen
0fde06c4d2 Merge remote-tracking branch 'upstream/main' into release_v0.40.0 2026-10-04 08:48:45 -07:00
Daniel Hiltgen
a00d083bb5
mlx: System one support (#18701)
* mlxrunner: restore System One scoring

Carry the MLX implementation and its tests from the original System One
commit. The API/compiler and llama-server implementation already exist on
the release branch, so retain those versions. Adapt the optional model test
to the renamed decision package and its explicit rendering/context setup.

(cherry picked from commit 26e546ddb3)

* Enable MLX System One and add regression coverage

* mlxrunner: add Laya support for System One

Import Laya checkpoints and implement bidirectional decision scoring.

* mlxrunner: release cached buffers after System One scoring

* decision: match Tev1 and Nimble publisher prompt formats

Select Tev1 prompts using renderer metadata and fix JSON formatting, with regression coverage for GGUF and MLX.

* mlx: support Clef and Clef Flash decision models

Add model import, quantization safeguards, and text/image scoring with the Clef joint decision head.

* support vision capabilities for decision models

* Make Clef scoring cancellable between prefill chunks

Preserve joint-head inputs and test cancellation, cleanup, and recovery.

* mlx: separate decision preparation and readout from forward

Let serial and batched scoring share model-owned preparation and readout
without duplicating architecture-specific logic in the runner.

* mlx: add Strands Decider support

* implement caching

---------

Co-authored-by: ParthSareen <parth.sareen@ollama.com>
2026-10-03 13:17:21 -07:00
Parth Sareen
42e911bc3d
docs: document image input for decision models (#18757) 2026-10-02 11:52:27 -07:00
Parth Sareen
e896a52a4f
docs: link to available decision models (#18758) 2026-10-02 11:51:55 -07:00
Daniel Hiltgen
1c345795ab Merge remote-tracking branch 'upstream/main' into release_v0.40.0 2026-10-01 16:51:30 -07:00
Jeffrey Morgan
e4c0d18eb8
models: add clef support (#18741) 2026-10-01 15:52:04 -07:00
Parth Sareen
1abe35e6e6
docs: document System One API (#18702) 2026-09-29 19:33:23 -07:00
Daniel Hiltgen
eadb68a609 Merge remote-tracking branch 'upstream/main' into release_v0.40.0
# Conflicts:
#	server/routes.go
2026-09-29 11:15:31 -07:00
Daniel Hiltgen
b3f78b7732
create: support explicit model capabilities (#18708)
Add CAPABILITY declarations to Modelfiles and an additive capabilities
field to create requests. Preserve declarations across GGUF and safetensors
creation, inheritance, and Modelfile export.

Require decision capability before scheduling System One requests instead
of matching Qwen architecture/renderer metadata. Retain main's GGUF-only
scoring restriction until the separate MLX runtime work lands.

Extracted from the capability foundation in 36d46a0c3 on system_one_mlx;
MLX scoring and manifest-list changes are intentionally separate.
2026-09-29 11:10:25 -07:00
Daniel Hiltgen
75b952780f llama-server: prepare to remove compatibility patch
Add manifest-list storage so runner-specific manifests can coexist under one tag while preserving existing v1 tags as best-effort downgrade anchors. Show/list/copy/remove/pull/push now understand runner and digest selection and transfer referenced child manifests and layers.

Add lazy local compatibility migration for legacy Ollama GGUFs into llama.cpp-compatible children, covering the patched model families and preserving parser/renderer, templates, projectors, media metadata, split GGUFs, and MTP/draft tensors where applicable.

Extend create/import/conversion paths for the same compatibility rules, harden manifest-list combine validation, and add focused manifest, migration, transfer, and integration coverage for first-load conversion plus chat/tools/vision/audio/embedding behavior.
2026-09-24 19:25:52 -07:00
Daniel Hiltgen
7af393188d
api: deprecate typical_p (#18627)
Switch from rejecting API requests to logging a warning.  Model creation still rejects the deprecated param.

Follow up from #18448 to remove the hard API failure.
2026-09-24 15:03:28 -07:00
Parth Sareen
c173758997
docs: document thinking control discovery (#18501) 2026-09-22 18:28:11 -07:00
Eva H
35bdad61df
docs: clarify integrations overview and add assistant icons (#18511) 2026-09-17 14:10:18 -07:00