mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-02 07:13:02 +00:00
8d9b9926d1
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
91 lines
3.1 KiB
YAML
91 lines
3.1 KiB
YAML
# Gateway config for the perf cases (tests/e2e/perf/test_perf_cases.py), the local twin of the
|
|
# proxy_config block in project-releaser's .buildkite/e2e-perf-gateway-values.yaml: the same model
|
|
# groups over the mock providers, the same two guardrails, so a laptop run and the lane read the same
|
|
# config. One deployment per mock provider pod; how long the mocks wait before answering is set by the
|
|
# case at setup (mock_latency), not here. Teams, users and keys are created by the case at run time.
|
|
general_settings:
|
|
master_key: os.environ/LITELLM_MASTER_KEY
|
|
database_url: os.environ/DATABASE_URL
|
|
store_model_in_db: true
|
|
proxy_config_reload_interval_seconds: 7
|
|
enable_jwt_auth: true
|
|
litellm_jwtauth:
|
|
user_id_jwt_field: sub
|
|
user_email_jwt_field: email
|
|
team_ids_jwt_field: groups
|
|
user_id_upsert: true
|
|
proxy_batch_write_at: 5
|
|
database_connection_pool_limit: 10
|
|
|
|
litellm_settings:
|
|
cache: true
|
|
cache_params:
|
|
type: redis
|
|
host: os.environ/REDIS_HOST
|
|
port: os.environ/REDIS_PORT
|
|
supported_call_types: []
|
|
callbacks:
|
|
- prometheus
|
|
- otel
|
|
service_callback:
|
|
- prometheus_system
|
|
require_auth_for_metrics_endpoint: false
|
|
drop_params: true
|
|
request_timeout: 120
|
|
|
|
router_settings:
|
|
num_retries: 2
|
|
retry_after: 0
|
|
allowed_fails: 3
|
|
cooldown_time: 5
|
|
routing_strategy: simple-shuffle
|
|
|
|
model_list:
|
|
- model_name: gpt-6-luna
|
|
litellm_params:
|
|
model: openai/gpt-6-luna
|
|
api_base: os.environ/E2E_PERF_MOCK_OPENAI_URL
|
|
api_key: perf-mock-not-checked
|
|
- model_name: gpt-6-luna-responses
|
|
litellm_params:
|
|
model: openai/responses/gpt-6-luna
|
|
api_base: os.environ/E2E_PERF_MOCK_OPENAI_URL
|
|
api_key: perf-mock-not-checked
|
|
- model_name: claude-sonnet-5
|
|
litellm_params:
|
|
model: anthropic/claude-sonnet-5
|
|
api_base: os.environ/E2E_PERF_MOCK_ANTHROPIC_URL
|
|
api_key: perf-mock-not-checked
|
|
- model_name: claude-sonnet-5-bedrock
|
|
litellm_params:
|
|
model: bedrock/anthropic.claude-sonnet-5
|
|
aws_bedrock_runtime_endpoint: os.environ/E2E_PERF_MOCK_BEDROCK_URL
|
|
aws_region_name: us-east-1
|
|
aws_access_key_id: perf-mock-not-checked
|
|
aws_secret_access_key: perf-mock-not-checked
|
|
- model_name: claude-sonnet-5-bedrock-converse
|
|
litellm_params:
|
|
model: bedrock/converse/anthropic.claude-sonnet-5
|
|
aws_bedrock_runtime_endpoint: os.environ/E2E_PERF_MOCK_BEDROCK_URL
|
|
aws_region_name: us-east-1
|
|
aws_access_key_id: perf-mock-not-checked
|
|
aws_secret_access_key: perf-mock-not-checked
|
|
guardrails:
|
|
- guardrail_name: perf-pre
|
|
litellm_params:
|
|
guardrail: generic_guardrail_api
|
|
mode: pre_call
|
|
api_base: os.environ/E2E_PERF_MOCK_GUARDRAIL_URL
|
|
default_on: true
|
|
streaming_end_of_stream_only: true
|
|
additional_provider_specific_params:
|
|
latency_s: 0.05
|
|
- guardrail_name: perf-post
|
|
litellm_params:
|
|
guardrail: generic_guardrail_api
|
|
mode: post_call
|
|
api_base: os.environ/E2E_PERF_MOCK_GUARDRAIL_URL
|
|
default_on: true
|
|
streaming_end_of_stream_only: true
|
|
additional_provider_specific_params:
|
|
latency_s: 0.05
|