Documentation
¶
Index ¶
Constants ¶
View Source
const DefaultBaseURL = "http://localhost:1235/v1"
Variables ¶
View Source
var ProtocolCapabilities = openai.ProtocolCapabilities{ Tools: true, Stream: true, StructuredOutput: true, Thinking: true, ThinkingFormat: openai.ThinkingWireFormatQwen, StrictThinkingModelMatch: true, }
Functions ¶
func LookupModelLimits ¶
func LookupModelLimits(ctx context.Context, baseURL, model string) limits.ModelLimits
Types ¶
type UtilizationProbe ¶ added in v0.10.9
type UtilizationProbe struct {
// contains filtered or unexported fields
}
UtilizationProbe queries oMLX server-root observability endpoints and normalizes them into the shared endpoint utilization shape.
func NewUtilizationProbe ¶ added in v0.10.9
func NewUtilizationProbe(baseURL string, client *http.Client) *UtilizationProbe
NewUtilizationProbe creates a probe for an OpenAI-compatible oMLX base URL.
func (*UtilizationProbe) Probe ¶ added in v0.10.9
func (p *UtilizationProbe) Probe(ctx context.Context) utilization.EndpointUtilization
Probe fetches /api/status from the server root and returns a normalized sample. Failures return stale or unknown utilization instead of surfacing endpoint unavailability.
Click to show internal directories.
Click to hide internal directories.