Devon Rifkin
5f57b0ef42
release / setup-environment (push) Has been cancelled
release / windows-depends (amd64, 11.3, https://developer.download.nvidia.com/compute/cuda/11.3.1/local_installers/cuda_11.3.1_465.89_win10.exe, windows, CUDA 11) (push) Has been cancelled
release / windows-depends (amd64, 12.8, https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe, windows, CUDA 12) (push) Has been cancelled
release / windows-depends (amd64, https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe, windows, ROCm 6, 6.2) (push) Has been cancelled
release / windows-depends (amd64, windows, CPU) (push) Has been cancelled
release / darwin-build (amd64, darwin) (push) Has been cancelled
release / darwin-build (arm64, darwin) (push) Has been cancelled
release / darwin-sign (push) Has been cancelled
release / windows-build (amd64, windows) (push) Has been cancelled
release / windows-build (arm64, windows) (push) Has been cancelled
release / windows-sign (push) Has been cancelled
release / linux-build (amd64, linux, archive) (push) Has been cancelled
release / linux-build (amd64, linux, rocm) (push) Has been cancelled
release / linux-build (arm64, linux, archive) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS
CGO_CXXFLAGS
GOFLAGS
, linux) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS
CGO_CXXFLAGS
GOFLAGS
FLAVOR=rocm
, linux, -rocm) (push) Has been cancelled
release / docker-build-push (arm64, CGO_CFLAGS
CGO_CXXFLAGS
GOFLAGS
, linux) (push) Has been cancelled
release / docker-merge-push () (push) Has been cancelled
release / docker-merge-push (-rocm) (push) Has been cancelled
release / trigger (push) Has been cancelled
release / release (push) Has been cancelled
- Both `/api/generate` and `/api/chat` now accept a `"think"` option that allows specifying whether thinking mode should be on or not - Templates get passed this new option so, e.g., qwen3's template can put `/think` or `/no_think` in the system prompt depending on the value of the setting - Models' thinking support is inferred by inspecting model templates. The prefix and suffix the parser uses to identify thinking support is also automatically inferred from templates - Thinking control & parsing is opt-in via the API to prevent breaking existing API consumers. If the `"think"` option is not specified, the behavior is unchanged from previous versions of ollama - Add parsing for thinking blocks in both streaming/non-streaming mode in both `/generate` and `/chat` - Update the CLI to make use of these changes. Users can pass `--think` or `--think=false` to control thinking, or during an interactive session they can use the commands `/set think` or `/set nothink` - A `--hidethinking` option has also been added to the CLI. This makes it easy to use thinking in scripting scenarios like `ollama run qwen3 --think --hidethinking "my question here"` where you just want to see the answer but still want the benefits of thinking models