Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Remove no longer supported max vram var
Daniel Hiltgencc269ba0943e
diff --git a/cmd/cmd.go b/cmd/cmd.goindex 2252a905e..b761d018f 100644--- a/cmd/cmd.go+++ b/cmd/cmd.go@@ -1344,7 +1344,6 @@ func NewCLI() *cobra.Command {envVars["OLLAMA_TMPDIR"],envVars["OLLAMA_FLASH_ATTENTION"],envVars["OLLAMA_LLM_LIBRARY"],- envVars["OLLAMA_MAX_VRAM"],})default:appendEnvDocs(cmd, envs)diff --git a/envconfig/config.go b/envconfig/config.goindex 62d661ebc..0abc69686 100644--- a/envconfig/config.go+++ b/envconfig/config.go@@ -43,8 +43,6 @@ var (MaxRunners int// Set via OLLAMA_MAX_QUEUE in the environmentMaxQueuedRequests int- // Set via OLLAMA_MAX_VRAM in the environment- MaxVRAM uint64// Set via OLLAMA_MODELS in the environmentModelsDir string// Set via OLLAMA_NOHISTORY in the environment@@ -89,7 +87,6 @@ func AsMap() map[string]EnvVar {"OLLAMA_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary, "Set LLM library to bypass autodetection"},"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners, "Maximum number of loaded models per GPU"},"OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueuedRequests, "Maximum number of queued requests"},- "OLLAMA_MAX_VRAM": {"OLLAMA_MAX_VRAM", MaxVRAM, "Maximum VRAM"},"OLLAMA_MODELS": {"OLLAMA_MODELS", ModelsDir, "The path to the models directory"},"OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory, "Do not preserve readline history"},"OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune, "Do not prune model blobs on startup"},@@ -194,16 +191,6 @@ func LoadConfig() {TmpDir = clean("OLLAMA_TMPDIR")- userLimit := clean("OLLAMA_MAX_VRAM")- if userLimit != "" {- avail, err := strconv.ParseUint(userLimit, 10, 64)- if err != nil {- slog.Error("invalid setting, ignoring", "OLLAMA_MAX_VRAM", userLimit, "error", err)- } else {- MaxVRAM = avail- }- }-LLMLibrary = clean("OLLAMA_LLM_LIBRARY")if onp := clean("OLLAMA_NUM_PARALLEL"); onp != "" {diff --git a/integration/concurrency_test.go b/integration/concurrency_test.goindex d66ba9f00..8593285b4 100644--- a/integration/concurrency_test.go+++ b/integration/concurrency_test.go@@ -69,7 +69,7 @@ func TestIntegrationConcurrentPredictOrcaMini(t *testing.T) {reqLimit := len(req)iterLimit := 5- vram := os.Getenv("OLLAMA_MAX_VRAM")+ vram := os.Getenv("OLLAMA_MAX_VRAM") // TODO - discover actual VRAMif vram != "" {max, err := strconv.ParseUint(vram, 10, 64)require.NoError(t, err)@@ -106,7 +106,7 @@ func TestIntegrationConcurrentPredictOrcaMini(t *testing.T) {// Stress the system if we know how much VRAM it has, and attempt to load more models than will fitfunc TestMultiModelStress(t *testing.T) {- vram := os.Getenv("OLLAMA_MAX_VRAM")+ vram := os.Getenv("OLLAMA_MAX_VRAM") // TODO - discover actual VRAMif vram == "" {t.Skip("OLLAMA_MAX_VRAM not specified, can't pick the right models for the stress test")}