SyslogSolution/syslog-harness
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

chore(ct116): capture production state (LiteLLM 1.99.1, nginx /ui //docs, router decommission, trove agent)

Browse Source
This commit is contained in:
agent-zero
2026-09-11 19:34:30 +00:00
parent 7cad063e27
commit 93e7605aa2
21 changed files with 196 additions and 1929 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LITELLM-MIGRATION-PLAN.md
+11 -11
View File
@@ -49,7 +49,7 @@
qwen3.6-35B qwen3.6-27B gemma-4-12b
qwen3.6-35B qwen3.6-27B gpu-vision
MoE/Strix Dense/RTX3090 VLM/RTX 5070
:8080 (llama) :8080 (llama) :8080 (llama)
:8090 (side) :8090 (side) :8090 (sidecar)
@@ -84,7 +84,7 @@
|-----|------|-----------|---------|------|---------|
| qwen3.6-35B-A3B (MoE) | 192.168.68.15 | :8080 | :8090 | Strix Halo | 262K |
| qwen3.6-27B-code (Dense) | 192.168.68.8 | :8080 | :8090 | RTX 3090 | 262K |
| gemma-4-12b (VLM) | 192.168.68.110 | :8080 | :8090 | RTX 5070 | 262K |
| gpu-vision (VLM) | 192.168.68.110 | :8080 | :8090 | RTX 5070 | 262K |
### 1.3 Existing LiteLLM POC on CT 116
@@ -249,9 +249,9 @@ model_list:
api_base: http://router:9000/v1
api_key: os.environ/ROUTER_API_KEY
- model_name: gemma-4-12b
- model_name: gpu-vision
litellm_params:
model: openai/gemma-4-12b
model: openai/gpu-vision
api_base: http://router:9000/v1
api_key: os.environ/ROUTER_API_KEY
@@ -298,9 +298,9 @@ router_settings:
# Fallback chains: LiteLLM retries down the chain when router returns saturated
# This gives accurate per-model metrics because router no longer silently reroutes
fallbacks:
- qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gemma-4-12b"]
- qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gemma-4-12b"]
- gemma-4-12b: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]
- qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gpu-vision"]
- qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gpu-vision"]
- gpu-vision: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]
# Cost tracking: map model names to per-token pricing for spend tracking
litellm_settings:
@@ -311,7 +311,7 @@ litellm_settings:
qwen3.6-27B-code:
input_cost_per_token: 0.0
output_cost_per_token: 0.0
gemma-4-12b:
gpu-vision:
input_cost_per_token: 0.0
output_cost_per_token: 0.0
# For internal cost allocation, set symbolic rates:
@@ -705,9 +705,9 @@ if req != "auto":
router_settings:
allowed_fails: 100
fallbacks:
- qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gemma-4-12b"]
- qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gemma-4-12b"]
- gemma-4-12b: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]
- qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gpu-vision"]
- qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gpu-vision"]
- gpu-vision: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]
```
### Result