Add TTFT & ITL Metrics for LLM Inference (#28)

Time-to-First-Token (TTFT) and Inter-Token Latency (ITL) metrics for LLM inference observability Metrics: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total Closes #31 #32 #33 --------- Co-authored-by: poimen <[email protected]> Reviewed-on: #28
2026-09-15 08:53:58 +00:00
parent 30e0a83a50
commit d439536ca9
22 changed files with 2224 additions and 199 deletions
@@ -36,6 +36,10 @@ type ModelUpstream struct {
 	Address string
 	// Path is the upstream path for this model (e.g., "/v1/chat/completions").
 	Path string
+	// UpstreamModel is the model name to send to the upstream server.
+	// If empty, the client-provided model name (Name) is used as-is.
+	// Use this when the upstream expects a different model name than clients send.
+	UpstreamModel string
 	// AuthRequired indicates whether this model requires JWT authentication.
 	AuthRequired bool
 }