Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
build: fix typo in override variable (#8031)
Daniel Hiltgen82a02e18d96c
diff --git a/docs/development.md b/docs/development.mdindex b1c944eed..e194dca0b 100644--- a/docs/development.md+++ b/docs/development.md@@ -53,7 +53,7 @@ If both v11 and v12 tookkits are detected, runners for both major versions will#### Older Linux CUDA (NVIDIA)-To support older GPUs with Compute Capability 3.5 or 3.7, you will need to use an older version of the Driver from [Unix Driver Archive](https://www.nvidia.com/en-us/drivers/unix/) (tested with 470) and [CUDA Toolkit Archive](https://developer.nvidia.com/cuda-toolkit-archive) (tested with cuda V11). When you build Ollama, you will need to set two make variable to adjust the minimum compute capability Ollama supports via `make -j 5 CUDA_ARCHITECTURES="35;37;50;52" EXTRA_GOLDLAGS="\"-X=github.com/ollama/ollama/discover.CudaComputeMajorMin=3\" \"-X=github.com/ollama/ollama/discover.CudaComputeMinorMin=5\""`. To find the Compute Capability of your older GPU, refer to [GPU Compute Capability](https://developer.nvidia.com/cuda-gpus).+To support older GPUs with Compute Capability 3.5 or 3.7, you will need to use an older version of the Driver from [Unix Driver Archive](https://www.nvidia.com/en-us/drivers/unix/) (tested with 470) and [CUDA Toolkit Archive](https://developer.nvidia.com/cuda-toolkit-archive) (tested with cuda V11). When you build Ollama, you will need to set two make variable to adjust the minimum compute capability Ollama supports via `make -j 5 CUDA_ARCHITECTURES="35;37;50;52" EXTRA_GOLDFLAGS="\"-X=github.com/ollama/ollama/discover.CudaComputeMajorMin=3\" \"-X=github.com/ollama/ollama/discover.CudaComputeMinorMin=5\""`. To find the Compute Capability of your older GPU, refer to [GPU Compute Capability](https://developer.nvidia.com/cuda-gpus).#### Linux ROCm (AMD)diff --git a/make/Makefile.ollama b/make/Makefile.ollamaindex 51ef7713f..678ea0d55 100644--- a/make/Makefile.ollama+++ b/make/Makefile.ollama@@ -6,7 +6,7 @@ exe: $(OLLAMA_EXE)dist_exe dist_ollama: $(DIST_OLLAMA_EXE)GO_DEPS=$(foreach dir,$(shell go list -deps -f '{{.Dir}}' . ),$(wildcard $(dir)/*.go))-CPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(TARGET_CPU_FLAGS))\" $(EXTRA_GOLDLAGS) $(TARGET_LDFLAGS)"+CPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(TARGET_CPU_FLAGS))\" $(EXTRA_GOLDFLAGS) $(TARGET_LDFLAGS)"$(OLLAMA_EXE) $(DIST_OLLAMA_EXE): TARGET_CPU_FLAGS=$(CUSTOM_CPU_FLAGS)$(OLLAMA_EXE) $(DIST_OLLAMA_EXE): $(COMMON_SRCS) $(COMMON_HDRS) $(GO_DEPS)diff --git a/make/gpu.make b/make/gpu.makeindex 9cfb45158..ef1c1345f 100644--- a/make/gpu.make+++ b/make/gpu.make@@ -5,7 +5,7 @@ dummy:$(error This makefile is not meant to build directly, but instead included in other Makefiles that set required variables)endif-GPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(GPU_RUNNER_CPU_FLAGS))\" $(EXTRA_GOLDLAGS) $(TARGET_LDFLAGS)"+GPU_GOFLAGS="-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=$(VERSION)\" \"-X=github.com/ollama/ollama/llama.CpuFeatures=$(subst $(space),$(comma),$(GPU_RUNNER_CPU_FLAGS))\" $(EXTRA_GOLDFLAGS) $(TARGET_LDFLAGS)"# TODO Unify how we handle dependencies in the dist/packaging and install flow# today, cuda is bundled, but rocm is split out. Should split them each out by runner