forked from vllm-project/semantic-router
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathconfig.agent-smoke.amd.yaml
More file actions
70 lines (66 loc) · 1.52 KB
/
config.agent-smoke.amd.yaml
File metadata and controls
70 lines (66 loc) · 1.52 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
version: v0.3
listeners:
- name: "agent-smoke-http-amd"
address: "0.0.0.0"
port: 8888
timeout: "60s"
providers:
defaults:
default_model: "smoke-model"
models:
- name: "smoke-model"
provider_model_id: "smoke-model"
backend_refs:
- name: "primary"
weight: 100
endpoint: "host.docker.internal:8000/v1"
protocol: "http"
routing:
modelCards:
- name: "smoke-model"
modality: "text"
decisions:
- name: "default-route"
description: "Minimal AMD default route for agent smoke validation"
priority: 100
rules:
operator: "AND"
conditions: []
modelRefs:
- model: "smoke-model"
use_reasoning: false
global:
stores:
semantic_cache:
enabled: false
model_catalog:
embeddings:
semantic:
mmbert_model_path: ""
qwen3_model_path: ""
gemma_model_path: ""
bert_model_path: ""
multimodal_model_path: ""
modules:
prompt_guard:
enabled: false
model_ref: ""
model_id: ""
jailbreak_mapping_path: ""
use_mmbert_32k: false
classifier:
domain:
model_ref: ""
model_id: ""
category_mapping_path: ""
use_mmbert_32k: false
pii:
model_ref: ""
model_id: ""
pii_mapping_path: ""
use_mmbert_32k: false
feedback_detector:
enabled: false
model_ref: ""
model_id: ""
use_mmbert_32k: false