From e2e09272912e2b40158bea36865fb6065bce56cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= Date: Fri, 21 Nov 2025 16:42:27 +0100 Subject: [PATCH] feat: update LiteLLM to use RunPod GPU via Tailscale MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Update api_base URLs from 100.100.108.13 to 100.121.199.88 (RunPod Tailscale IP) - All self-hosted models (qwen-2.5-7b, flux-schnell, musicgen-medium) now route through Tailscale VPN - Tested and verified connectivity between VPS and RunPod GPU orchestrator 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude --- ai/litellm-config.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml index 134375e..4dab6ed 100644 --- a/ai/litellm-config.yaml +++ b/ai/litellm-config.yaml @@ -33,7 +33,7 @@ model_list: - model_name: qwen-2.5-7b litellm_params: model: openai/qwen-2.5-7b - api_base: http://100.100.108.13:9000/v1 # Orchestrator endpoint + api_base: http://100.121.199.88:9000/v1 # RunPod GPU via Tailscale api_key: dummy rpm: 1000 tpm: 100000 @@ -42,7 +42,7 @@ model_list: - model_name: flux-schnell litellm_params: model: openai/dall-e-3 # OpenAI-compatible mapping - api_base: http://100.100.108.13:9000/v1 # Orchestrator endpoint + api_base: http://100.121.199.88:9000/v1 # RunPod GPU via Tailscale api_key: dummy rpm: 100 max_parallel_requests: 3 @@ -51,7 +51,7 @@ model_list: - model_name: musicgen-medium litellm_params: model: openai/musicgen-medium - api_base: http://100.100.108.13:9000/v1 # Orchestrator endpoint + api_base: http://100.121.199.88:9000/v1 # RunPod GPU via Tailscale api_key: dummy rpm: 50 max_parallel_requests: 1