misc/ollama0.40.7

misc/ollama: update 0.40.8 → 0.40.11

misc/ollama: update 0.40.7 → 0.40.8

ChangeLog: https://github.com/ollama/ollama/releases/tag/v0.40.8

misc/ollama: update 0.40.6 → 0.40.7

ChangeLog: https://github.com/ollama/ollama/releases/tag/v0.40.7

various: Bump Go ports for Go 1.26.10 / 1.27.3

misc/ollama: update 0.40.5 → 0.40.6

ChangeLog: https://github.com/ollama/ollama/releases/tag/v0.40.6

misc/ollama: update 0.40.4 → 0.40.5

misc/ollama: Remove USE_LDCONFIG

ollama installs privare shared libs that aren't supposed to be
discoverable or used by others.

misc/ollama: update 0.40.3 → 0.40.4

ChangeLog: https://github.com/ollama/ollama/releases/tag/v0.40.4

misc/ollama: update 0.40.2 → 0.40.3

misc/ollama: update 0.40.0 → 0.40.2

various: Bump Go ports

misc/ollama: correct typo

misc/ollama: add comment

misc/ollama: update 0.34.3 → 0.40.0

various: Drop Go 1.26+ version pin

This is a nop since 1.26 is the oldest supported version.

misc/ollama: update 0.34.0 → 0.34.3

misc/ollama: update 0.32.5 → 0.34.0

MLX image generation is now officially disabled hy the upstream
with the promise that it will come back once issues are resolved.

The VULKAN option is now enabled again since compilation issues
were resolved.

ChangeLog: https://github.com/ollama/ollama/releases/tag/v0.34.0

many: Bump go ports for 1.26.8 and 1.27.1

various: Bump go ports for go-1.25.14 / 1.26.7

various: Bump go ports for go-1.25.13 / 1.26.6

misc/ollama: VULKAN option is broken

misc/ollama: update 0.32.4 → 0.32.5

misc/ollama: update 0.32.3 → 0.32.4

misc/ollama: update 0.32.1 → 0.32.3

What's Changed:
* Fixed model downloads that stall before sending data.
* Improved integrations: restored Claude Code Channels,
  fixed Anthropic thinking streams, and made Hermes
  Desktop respect --force-build.
* Expanded GPU support with CUDA on Windows ARM64, B200
  support through CUDA 12, and lower memory use on Linux
  CUDA/ROCm iGPUs.
* Added chat, thinking, and tool calling support for
  Laguna 2.1 models, including a Metal inference fix.
* Fixed GLM tool calls being silently dropped at the end
  of generation.
* Updated the MLX and llama.cpp engines.

Changelog: https://github.com/ollama/ollama/compare/v0.32.1...v0.32.3

misc/ollama: update 0.32.0 → 0.32.1

misc/ollama: Only for amd64 for now

misc/ollama: update 0.31.2 → 0.32.0

misc/ollama: Update COMMENT

various: Bump go ports for go-1.25.12 / 1.26.5

misc/ollama: update 0.31.1 → 0.31.2

misc/ollama: update 0.31.0 → 0.31.1

misc/ollama: update 0.30.11 → 0.31.0

misc/ollama: update 0.30.10 → 0.30.11

misc/ollama: Make ollama service use the 'nobody' user by dfault

Suggested by:	Adrian Chadd <adrian@freebsd.org>

misc/ollama: Update pkg-message and pkg-descr

misc/ollama: update 0.30.9 → 0.30.10

misc/ollama: Apply one missing patch

This fixes run-time failures for some models.

misc/ollama: update 0.30.7 → 0.30.9

misc/ollama: update 0.30.6 → 0.30.7

misc/ollama: update 0.30.5 → 0.30.6

misc/ollama: update 0.30.4 → 0.30.5

misc/ollama: update 0.30.0 → 0.30.4

various: Bump go ports for go-1.25.11 / go-1.26.4

misc/ollama: update 0.24.0 → 0.30.0

misc/ollama: update 0.23.3 → 0.24.0

*/*: bump PORTREVISION after the upgrade of OpenBLAS

misc/ollama: update 0.23.2 → 0.23.3

various: Bump ports for Go 1.26.3

misc/ollama: update 0.23.1 → 0.23.2

misc/ollama: update 0.23.0 → 0.23.1